AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2020
Augello, Agnese; Infantino, Ignazio; Pilato, Giovanni; Vella, Filippo
Sensing the Web for Induction of Association Rules and Their Composition through Ensemble Techniques Proceedings Article
In: A.V., Klimov V. V. Samsonovich (Ed.): Procedia Computer Science, pp. 851–859, Elsevier B.V., 2020.
Abstract | Links | BibTeX | Tags: Association Rules, Semantic Computing
@inproceedings{augelloSensingWebInduction2020,
title = {Sensing the Web for Induction of Association Rules and Their Composition through Ensemble Techniques},
author = { Agnese Augello and Ignazio Infantino and Giovanni Pilato and Filippo Vella},
editor = { Klimov V.V. Samsonovich A.V.},
doi = {10.1016/j.procs.2020.02.152},
year = {2020},
date = {2020-01-01},
booktitle = {Procedia Computer Science},
volume = {169},
pages = {851--859},
publisher = {Elsevier B.V.},
abstract = {Starting from geophysical data collected from heterogeneous sources, such as meteorological stations and information gathered from the web, we seek unknown connections between the sampled values through the extraction of association rules. These rules imply the co-occurrence of two or more symbols in the same representation, and the rule confidence may vary according to the collected data. We propose, starting from traditional algorithms such as FP-Growth and Apriori, the creation of complex association rules through boosting of simpler ones. The composition enables the creation of rules that are robust and let emerge a larger number of interesting rules. textcopyright 2020 The Authors. Published by Elsevier B.V.},
keywords = {Association Rules, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
Starting from geophysical data collected from heterogeneous sources, such as meteorological stations and information gathered from the web, we seek unknown connections between the sampled values through the extraction of association rules. These rules imply the co-occurrence of two or more symbols in the same representation, and the rule confidence may vary according to the collected data. We propose, starting from traditional algorithms such as FP-Growth and Apriori, the creation of complex association rules through boosting of simpler ones. The composition enables the creation of rules that are robust and let emerge a larger number of interesting rules. textcopyright 2020 The Authors. Published by Elsevier B.V.
Trifir`o, Irene; Augello, Agnese; Maniscalco, Umberto; Pilato, Giovanni; Vella, Filippo; Meo, Rosa
How Are You? How a Robot Can Learn to Express Its Own Roboceptions Proceedings Article
In: Cristiani, Matteo; Toro, Carlos; Zanni-Merk, Cecilia; Howlett, Robert J.; Jain, Lakhmi C. (Ed.): Procedia Computer Science, pp. 480–489, Elsevier B.V., 2020.
Abstract | Links | BibTeX | Tags: Human computer interaction, Knowledge Representation, Latent Semantic Analysis, Natural Language Processing, Robotics, Semantic Computing, Social Robots
@inproceedings{trifiroHowAreYou2020,
title = {How Are You? How a Robot Can Learn to Express Its Own Roboceptions},
author = { Irene Trifir{`o} and Agnese Augello and Umberto Maniscalco and Giovanni Pilato and Filippo Vella and Rosa Meo},
editor = { Matteo Cristiani and Carlos Toro and Cecilia {Zanni-Merk} and Robert J. Howlett and Lakhmi C. Jain},
doi = {10.1016/j.procs.2020.08.050},
year = {2020},
date = {2020-01-01},
booktitle = {Procedia Computer Science},
volume = {176},
pages = {480--489},
publisher = {Elsevier B.V.},
abstract = {This work is framed on investigating how a robot can learn associations between linguistic elements, such as words or sentences, and its bodily perceptions, that we named ``roboceptions''. We discuss the possibility of defining such a process of an association through the interaction with human beings. By interacting with a user, the robot can learn to ascribe a meaning to its roboceptions to express them in natural language. Such a process could then be used by the robot in a verbal interaction to detect some words recalling the previously experimented roboceptions. In this paper, we discuss a Dual-NMT approach to realize such an association. However, it requires adequate training corpus. For this reason, we consider two different phases towards the realization of the system, and we show the results of the first phase, comparing two approaches: one based on the Latent Semantic Analysis paradigm and one based on the Random Indexing methodology.},
keywords = {Human computer interaction, Knowledge Representation, Latent Semantic Analysis, Natural Language Processing, Robotics, Semantic Computing, Social Robots},
pubstate = {published},
tppubtype = {inproceedings}
}
This work is framed on investigating how a robot can learn associations between linguistic elements, such as words or sentences, and its bodily perceptions, that we named ``roboceptions''. We discuss the possibility of defining such a process of an association through the interaction with human beings. By interacting with a user, the robot can learn to ascribe a meaning to its roboceptions to express them in natural language. Such a process could then be used by the robot in a verbal interaction to detect some words recalling the previously experimented roboceptions. In this paper, we discuss a Dual-NMT approach to realize such an association. However, it requires adequate training corpus. For this reason, we consider two different phases towards the realization of the system, and we show the results of the first phase, comparing two approaches: one based on the Latent Semantic Analysis paradigm and one based on the Random Indexing methodology.
2019
Augello, Agnese; Pilato, Giovanni
An Annotated Corpus of Stories and Gestures for a Robotic Storyteller Proceedings Article
In: Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019, pp. 630–635, Institute of Electrical and Electronics Engineers Inc., 2019, ISBN: 978-1-5386-9245-5.
Abstract | Links | BibTeX | Tags: Annotated Corpus, Robotics, Semantic Computing, Storytelling Robots
@inproceedings{augelloAnnotatedCorpusStories2019,
title = {An Annotated Corpus of Stories and Gestures for a Robotic Storyteller},
author = { Agnese Augello and Giovanni Pilato},
doi = {10.1109/IRC.2019.00127},
isbn = {978-1-5386-9245-5},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019},
pages = {630--635},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {This paper describes a system which has been used to automatically create an annotated corpus of stories. This corpus can be exploited by a robotic storyteller. In a first phase stories were retrieved from a repository. The textual content of each story was semantically analyzed in order to locate meaningful terms in the sentences that can be accompanied by proper gestures and possible emotions that can be expressed. Once the whole story is properly labelled, it can be dramatized by a robot storyteller. We discuss a demonstration of the use of this approach with NarRob, a storyteller robot that we have designed within our institute. textcopyright 2019 IEEE.},
keywords = {Annotated Corpus, Robotics, Semantic Computing, Storytelling Robots},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper describes a system which has been used to automatically create an annotated corpus of stories. This corpus can be exploited by a robotic storyteller. In a first phase stories were retrieved from a repository. The textual content of each story was semantically analyzed in order to locate meaningful terms in the sentences that can be accompanied by proper gestures and possible emotions that can be expressed. Once the whole story is properly labelled, it can be dramatized by a robot storyteller. We discuss a demonstration of the use of this approach with NarRob, a storyteller robot that we have designed within our institute. textcopyright 2019 IEEE.
2017
Gentile, Vito; Milazzo, Fabrizio; Sorce, Salvatore; Gentile, Antonio; Augello, Agnese; Pilato, Giovanni
Body Gestures and Spoken Sentences: A Novel Approach for Revealing User's Emotions Proceedings Article
In: Proceedings - IEEE 11th International Conference on Semantic Computing, ICSC 2017, pp. 69–72, Institute of Electrical and Electronics Engineers Inc., 2017, ISBN: 978-1-5090-4896-0.
Abstract | Links | BibTeX | Tags: Emotion Analysis, Emotion Recognition, Facial Expressions, Gestural user interfaces, Human computer interaction, Semantic Computing, Sentiment Analysis
@inproceedings{gentileBodyGesturesSpoken2017,
title = {Body Gestures and Spoken Sentences: A Novel Approach for Revealing User's Emotions},
author = { Vito Gentile and Fabrizio Milazzo and Salvatore Sorce and Antonio Gentile and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2017.14},
isbn = {978-1-5090-4896-0},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings - IEEE 11th International Conference on Semantic Computing, ICSC 2017},
pages = {69--72},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have contributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be used to reveal user's emotions from gestures. textcopyright 2017 IEEE.},
keywords = {Emotion Analysis, Emotion Recognition, Facial Expressions, Gestural user interfaces, Human computer interaction, Semantic Computing, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have contributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be used to reveal user's emotions from gestures. textcopyright 2017 IEEE.
2016
Augello, Agnese; Cuzzocrea, Alfredo; Pilato, Giovanni; Spiccia, Carmelo; Vassallo, Giorgio
An Innovative Similarity Measure for Sentence Plagiarism Detection Proceedings Article
In: Gervasi, O; Murgante, B; Misra, S; relax AMAC Rocha,; relax CM Torre,; Tanier, D; relax BO Apduhan,; Stankova, E; Wang, S (Ed.): COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2016, PT V, pp. 552–566, SPRINGER INTERNATIONAL PUBLISHING AG, GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND, 2016, ISBN: 978-3-319-42092-9.
Abstract | Links | BibTeX | Tags: Plagiarism Detection, Semantic Computing
@inproceedings{augelloInnovativeSimilarityMeasure2016,
title = {An Innovative Similarity Measure for Sentence Plagiarism Detection},
author = { Agnese Augello and Alfredo Cuzzocrea and Giovanni Pilato and Carmelo Spiccia and Giorgio Vassallo},
editor = { O Gervasi and B Murgante and S Misra and {relax AMAC} Rocha and {relax CM} Torre and D Tanier and {relax BO} Apduhan and E Stankova and S Wang},
doi = {10.1007/978-3-319-42092-9_42},
isbn = {978-3-319-42092-9},
year = {2016},
date = {2016-01-01},
booktitle = {COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2016, PT V},
volume = {9790},
pages = {552--566},
publisher = {SPRINGER INTERNATIONAL PUBLISHING AG},
address = {GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND},
series = {Lecture Notes in Computer Science},
abstract = {We propose and experimentally assess Semantic Word Error Rate (SWER), an innovative similarity measure for sentence plagiarism detection. SWER introduces a complex approach based on latent semantic analysis, which is capable of outperforming the accuracy of competitor methods in plagiarism detection. We provide principles and functionalities of SWER, and we complement our analytical contribution by means of a significant preliminary experimental analysis. Derived results are promising, and confirm to use the goodness of our proposal.},
keywords = {Plagiarism Detection, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
We propose and experimentally assess Semantic Word Error Rate (SWER), an innovative similarity measure for sentence plagiarism detection. SWER introduces a complex approach based on latent semantic analysis, which is capable of outperforming the accuracy of competitor methods in plagiarism detection. We provide principles and functionalities of SWER, and we complement our analytical contribution by means of a significant preliminary experimental analysis. Derived results are promising, and confirm to use the goodness of our proposal.
Spiccia, Carmelo; Augello, Agnese; Pilato, Giovanni; Vassallo, Giorgio
Semantic Word Error Rate for Sentence Similarity Proceedings Article
In: Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016, pp. 266–269, Institute of Electrical and Electronics Engineers Inc., 2016, ISBN: 978-1-5090-0661-8.
Abstract | Links | BibTeX | Tags: Human computer interaction, Latent Semantic Analysis, Natural Language Processing, Semantic Computing
@inproceedings{spicciaSemanticWordError2016,
title = {Semantic Word Error Rate for Sentence Similarity},
author = { Carmelo Spiccia and Agnese Augello and Giovanni Pilato and Giorgio Vassallo},
doi = {10.1109/ICSC.2016.11},
isbn = {978-1-5090-0661-8},
year = {2016},
date = {2016-01-01},
booktitle = {Proceedings - 2016 IEEE 10th International Conference on Semantic Computing, ICSC 2016},
pages = {266--269},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Sentence similarity measures have applications in several tasks, including: Machine Translation, Paraphrase Identification, Speech Recognition, Question-answering and Text Summarization. However, measures designed for these tasks are aimed at assessing equivalence rather than resemblance, partly departing from human cognition of similarity. While this is reasonable for these activities, it hinders the applicability of sentence similarity measures to other tasks. We therefore propose a new sentence similarity measure specifically designed for resemblance evaluation, in order to cover these fields better. Experimental results are discussed. textcopyright 2016 IEEE.},
keywords = {Human computer interaction, Latent Semantic Analysis, Natural Language Processing, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
Sentence similarity measures have applications in several tasks, including: Machine Translation, Paraphrase Identification, Speech Recognition, Question-answering and Text Summarization. However, measures designed for these tasks are aimed at assessing equivalence rather than resemblance, partly departing from human cognition of similarity. While this is reasonable for these activities, it hinders the applicability of sentence similarity measures to other tasks. We therefore propose a new sentence similarity measure specifically designed for resemblance evaluation, in order to cover these fields better. Experimental results are discussed. textcopyright 2016 IEEE.
Spiccia, Carmelo; Augello, Agnese; Pilato, Giovanni
A Word Prediction Methodology Based on Posgrams Journal Article
In: Communications in Computer and Information Science, vol. 631, pp. 139–154, 2016, ISSN: 18650929.
Abstract | Links | BibTeX | Tags: Knowledge Management, Semantic Computing
@article{spicciaWordPredictionMethodology2016,
title = {A Word Prediction Methodology Based on Posgrams},
author = { Carmelo Spiccia and Agnese Augello and Giovanni Pilato},
editor = { Fred A. Dietz J.L.G. Liu K. Aveiro D. Filipe J.},
doi = {10.1007/978-3-319-52758-1_9},
issn = {18650929},
year = {2016},
date = {2016-01-01},
journal = {Communications in Computer and Information Science},
volume = {631},
pages = {139--154},
abstract = {This work introduces a two steps methodology for the prediction of missing words in incomplete sentences. In a first step the number of candidate words is restricted to the ones fulfilling the predicted part of speech; to this aim a novel algorithm based on ``posgrams'' analysis is also proposed. Then, in a second step, a word prediction algorithm is applied on the reduced words set. The work quantifies the advantages in predicting a word part of speech before predicting the word itself, in terms of accuracy and execution time. The methodology can be applied in several tasks, such as Text Autocompletion, Speech Recognition and Optical Text Recognition. textcopyright Springer International Publishing AG 2016.},
keywords = {Knowledge Management, Semantic Computing},
pubstate = {published},
tppubtype = {article}
}
This work introduces a two steps methodology for the prediction of missing words in incomplete sentences. In a first step the number of candidate words is restricted to the ones fulfilling the predicted part of speech; to this aim a novel algorithm based on ``posgrams'' analysis is also proposed. Then, in a second step, a word prediction algorithm is applied on the reduced words set. The work quantifies the advantages in predicting a word part of speech before predicting the word itself, in terms of accuracy and execution time. The methodology can be applied in several tasks, such as Text Autocompletion, Speech Recognition and Optical Text Recognition. textcopyright Springer International Publishing AG 2016.
2015
Ditta, Marilena; Milazzo, Fabrizio; Raví, Valentina; Pilato, Giovanni; Augello, Agnese
Data-Driven Relation Discovery from Unstructured Texts Proceedings Article
In: A., Filipe J. Liu K. Aveiro D. Dietz J. Filipe J. Fred (Ed.): IC3K 2015 - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, pp. 597–602, SciTePress, 2015, ISBN: 978-989-758-158-8.
Abstract | BibTeX | Tags: Knowledge Management, Knowledge Representation, Latent Semantic Analysis, Semantic Computing
@inproceedings{dittaDatadrivenRelationDiscovery2015,
title = {Data-Driven Relation Discovery from Unstructured Texts},
author = { Marilena Ditta and Fabrizio Milazzo and Valentina Raví and Giovanni Pilato and Agnese Augello},
editor = { Filipe J. Liu K. Aveiro D. Dietz J. Filipe J. Fred A.},
isbn = {978-989-758-158-8},
year = {2015},
date = {2015-01-01},
booktitle = {IC3K 2015 - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management},
volume = {1},
pages = {597--602},
publisher = {SciTePress},
abstract = {This work proposes a data driven methodology for the extraction of subject-verb-object triplets from a text corpus. Previous works on the field solved the problem by means of complex learning algorithms requiring hand-crafted examples; our proposal completely avoids learning triplets from a dataset and is built on top of a well-known baseline algorithm designed by Delia Rusu et al.. The baseline algorithm uses only syntactic information for generating triplets and is characterized by a very low precision i.e., very few triplets are meaningful. Our idea is to integrate the semantics of the words with the aim of filtering out the wrong triplets, thus increasing the overall precision of the system. The algorithm has been tested over the Reuters Corpus and has it as shown good performance with respect to the baseline algorithm for triplet extraction. textcopyright 2015 by SCITEPRESS - Science and Technology Publications, Lda.},
keywords = {Knowledge Management, Knowledge Representation, Latent Semantic Analysis, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
This work proposes a data driven methodology for the extraction of subject-verb-object triplets from a text corpus. Previous works on the field solved the problem by means of complex learning algorithms requiring hand-crafted examples; our proposal completely avoids learning triplets from a dataset and is built on top of a well-known baseline algorithm designed by Delia Rusu et al.. The baseline algorithm uses only syntactic information for generating triplets and is characterized by a very low precision i.e., very few triplets are meaningful. Our idea is to integrate the semantics of the words with the aim of filtering out the wrong triplets, thus increasing the overall precision of the system. The algorithm has been tested over the Reuters Corpus and has it as shown good performance with respect to the baseline algorithm for triplet extraction. textcopyright 2015 by SCITEPRESS - Science and Technology Publications, Lda.
Spiccia, Carmelo; Augello, Agnese; Pilato, Giovanni
Posgram Driven Word Prediction Proceedings Article
In: A., Dietz J. Aveiro D. Liu K. Filipe J. Filipe J. Fred (Ed.): IC3K 2015 - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, pp. 589–596, SciTePress, 2015, ISBN: 978-989-758-158-8.
Abstract | Links | BibTeX | Tags: Knowledge Management, Knowledge Representation, Semantic Computing
@inproceedings{spicciaPosgramDrivenWord2015,
title = {Posgram Driven Word Prediction},
author = { Carmelo Spiccia and Agnese Augello and Giovanni Pilato},
editor = { Dietz J. Aveiro D. Liu K. Filipe J. Filipe J. Fred A.},
doi = {10.5220/0005613305890596},
isbn = {978-989-758-158-8},
year = {2015},
date = {2015-01-01},
booktitle = {IC3K 2015 - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management},
volume = {1},
pages = {589--596},
publisher = {SciTePress},
abstract = {Several word prediction algorithms have been described in literature for automatic sentence completion from a finite candidate words set. However, at the best of our knowledge, very little or no work has been done on reducing the cardinality of this set. To address this issue, we use posgrams to predict the part of speech of the missing word first. Candidate words are then restricted to the ones fulfilling the predicted part of speech. We show how this additional step can improve the processing speed and the accuracy of word predictors. Experimental results are provided for the Italian language. textcopyright 2015 by SCITEPRESS - Science and Technology Publications, Lda.},
keywords = {Knowledge Management, Knowledge Representation, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
Several word prediction algorithms have been described in literature for automatic sentence completion from a finite candidate words set. However, at the best of our knowledge, very little or no work has been done on reducing the cardinality of this set. To address this issue, we use posgrams to predict the part of speech of the missing word first. Candidate words are then restricted to the ones fulfilling the predicted part of speech. We show how this additional step can improve the processing speed and the accuracy of word predictors. Experimental results are provided for the Italian language. textcopyright 2015 by SCITEPRESS - Science and Technology Publications, Lda.
Spiccia, Carmelo; Augello, Agnese; Pilato, Giovanni; Vassallo, Giorgio
A Word Prediction Methodology for Automatic Sentence Completion Proceedings Article
In: M.S., Li T. Wang W. Kankanhalli (Ed.): Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015, pp. 240–243, Institute of Electrical and Electronics Engineers Inc., 2015, ISBN: 978-1-4799-7935-6.
Abstract | Links | BibTeX | Tags: Computational Linguistics, Language Model, Latent Semantic Analysis, Semantic Computing, Semantic Spaces
@inproceedings{spicciaWordPredictionMethodology2015,
title = {A Word Prediction Methodology for Automatic Sentence Completion},
author = { Carmelo Spiccia and Agnese Augello and Giovanni Pilato and Giorgio Vassallo},
editor = { Li T. Wang W. Kankanhalli M.S.},
doi = {10.1109/ICOSC.2015.7050813},
isbn = {978-1-4799-7935-6},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015},
pages = {240--243},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Word prediction generally relies on n-grams occurrence statistics, which may have huge data storage requirements and does not take into account the general meaning of the text. We propose an alternative methodology, based on Latent Semantic Analysis, to address these issues. An asymmetric Word-Word frequency matrix is employed to achieve higher scalability with large training datasets than the classic Word-Document approach. We propose a function for scoring candidate terms for the missing word in a sentence. We show how this function approximates the probability of occurrence of a given candidate word. Experimental results show that the proposed approach outperforms non neural network language models. textcopyright 2015 IEEE.},
keywords = {Computational Linguistics, Language Model, Latent Semantic Analysis, Semantic Computing, Semantic Spaces},
pubstate = {published},
tppubtype = {inproceedings}
}
Word prediction generally relies on n-grams occurrence statistics, which may have huge data storage requirements and does not take into account the general meaning of the text. We propose an alternative methodology, based on Latent Semantic Analysis, to address these issues. An asymmetric Word-Word frequency matrix is employed to achieve higher scalability with large training datasets than the classic Word-Document approach. We propose a function for scoring candidate terms for the missing word in a sentence. We show how this function approximates the probability of occurrence of a given candidate word. Experimental results show that the proposed approach outperforms non neural network language models. textcopyright 2015 IEEE.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
A System for Analysis and Comparison of Social Network Profiles Proceedings Article
In: M.S., Li T. Wang W. Kankanhalli (Ed.): Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015, pp. 109–115, Institute of Electrical and Electronics Engineers Inc., 2015, ISBN: 978-1-4799-7935-6.
Abstract | Links | BibTeX | Tags: Semantic Computing, User Profiling
@inproceedings{terranaSystemAnalysisComparison2015,
title = {A System for Analysis and Comparison of Social Network Profiles},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
editor = { Li T. Wang W. Kankanhalli M.S.},
doi = {10.1109/ICOSC.2015.7050787},
isbn = {978-1-4799-7935-6},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015},
pages = {109--115},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {This work proposes a system for the analysis and the comparison of users profiles in social networks. Posts are extracted and analyzed in order to detect similar contents, like topics, sentiments and writing styles. A case study regarding the analysis of the authenticity of profiles of the Italian prime minister in different social networks is illustrated. textcopyright 2015 IEEE.},
keywords = {Semantic Computing, User Profiling},
pubstate = {published},
tppubtype = {inproceedings}
}
This work proposes a system for the analysis and the comparison of users profiles in social networks. Posts are extracted and analyzed in order to detect similar contents, like topics, sentiments and writing styles. A case study regarding the analysis of the authenticity of profiles of the Italian prime minister in different social networks is illustrated. textcopyright 2015 IEEE.
2014
Augello, Agnese; Gentile, Manuel; Pilato, Giovanni; Vassallo, Giorgio
A Geometric Algebra Based Distributional Model to Encode Sentences Semantics Proceedings Article
In: Lai, C; Giuliani, A; Semeraro, G (Ed.): DISTRIBUTED SYSTEMS AND APPLICATIONS OF INFORMATION FILTERING AND RETRIEVAL: DART 2012: REVISED AND INVITED PAPERS, pp. 101–114, SPRINGER-VERLAG BERLIN, HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY, 2014, ISBN: 978-3-642-40620-1.
Abstract | Links | BibTeX | Tags: Natural Language Processing, Semantic Computing, Semantic Spaces
@inproceedings{augelloGeometricAlgebraBased2014,
title = {A Geometric Algebra Based Distributional Model to Encode Sentences Semantics},
author = { Agnese Augello and Manuel Gentile and Giovanni Pilato and Giorgio Vassallo},
editor = { C Lai and A Giuliani and G Semeraro},
doi = {10.1007/978-3-642-40621-8_6},
isbn = {978-3-642-40620-1},
year = {2014},
date = {2014-01-01},
booktitle = {DISTRIBUTED SYSTEMS AND APPLICATIONS OF INFORMATION FILTERING AND RETRIEVAL: DART 2012: REVISED AND INVITED PAPERS},
volume = {515},
pages = {101--114},
publisher = {SPRINGER-VERLAG BERLIN},
address = {HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY},
series = {Studies in Computational Intelligence},
abstract = {Word space models are used to encode the semantics of natural language elements by means of high dimensional vectors [23]. Latent Semantic Analysis (LSA) methodology [15] is well known and widely used for its generalization properties. Despite of its good performance in several applications, the model induced by LSA ignores dynamic changes in sentences meaning that depend on the order of the words, because it is based on a bag of words analysis. In this chapter we present a technique that exploits LSA-based semantic spaces and geometric algebra in order to obtain a sub-symbolic encoding of sentences taking into account the words sequence in the sentence.},
keywords = {Natural Language Processing, Semantic Computing, Semantic Spaces},
pubstate = {published},
tppubtype = {inproceedings}
}
Word space models are used to encode the semantics of natural language elements by means of high dimensional vectors [23]. Latent Semantic Analysis (LSA) methodology [15] is well known and widely used for its generalization properties. Despite of its good performance in several applications, the model induced by LSA ignores dynamic changes in sentences meaning that depend on the order of the words, because it is based on a bag of words analysis. In this chapter we present a technique that exploits LSA-based semantic spaces and geometric algebra in order to obtain a sub-symbolic encoding of sentences taking into account the words sequence in the sentence.
Augello, Agnese; Infantino, Ignazio; Pilato, Giovanni; Rizzo, Riccardo; Vella, Filippo
Robotic Creativity Driven by Motivation and Semantic Analysis Proceedings Article
In: Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014, pp. 285–289, IEEE Computer Society, 2014, ISBN: 978-1-4799-4002-8.
Abstract | Links | BibTeX | Tags: Artificial intelligence, Chatbots, Cognitive Architectures, Computational Creativity, Creative Agents, Motivation, Natural Language Processing, PSI, Semantic Computing, Social Robots
@inproceedings{augelloRoboticCreativityDriven2014,
title = {Robotic Creativity Driven by Motivation and Semantic Analysis},
author = { Agnese Augello and Ignazio Infantino and Giovanni Pilato and Riccardo Rizzo and Filippo Vella},
doi = {10.1109/ICSC.2014.58},
isbn = {978-1-4799-4002-8},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014},
pages = {285--289},
publisher = {IEEE Computer Society},
abstract = {The paper proposes a system architecture for artificial creativity that enables a robot to perform portraits. The proposed cognitive architecture is inspired by the PSI model, and it requires that the motivation of the robot in the execution of its tasks is influenced by urges. Such parameters depend on both internal and external evaluation mechanisms. The system is a premise for the development of an artificial artist able to develop a personality and a behavior that depends on its experience of successes and failures (competence), and the availability of different painting techniques (certainty). The creative execution is driven by the motivation arising from the urges, and the perception of the work being executed or performed. The external evaluation is obtained by analyzing the opinions expressed in natural language from people watching the realized portrait. textcopyright 2014 IEEE.},
keywords = {Artificial intelligence, Chatbots, Cognitive Architectures, Computational Creativity, Creative Agents, Motivation, Natural Language Processing, PSI, Semantic Computing, Social Robots},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper proposes a system architecture for artificial creativity that enables a robot to perform portraits. The proposed cognitive architecture is inspired by the PSI model, and it requires that the motivation of the robot in the execution of its tasks is influenced by urges. Such parameters depend on both internal and external evaluation mechanisms. The system is a premise for the development of an artificial artist able to develop a personality and a behavior that depends on its experience of successes and failures (competence), and the availability of different painting techniques (certainty). The creative execution is driven by the motivation arising from the urges, and the perception of the work being executed or performed. The external evaluation is obtained by analyzing the opinions expressed in natural language from people watching the realized portrait. textcopyright 2014 IEEE.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
Automatic Unsupervised Polarity Detection on a Twitter Data Stream Proceedings Article
In: Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014, pp. 128–134, IEEE Computer Society, 2014, ISBN: 978-1-4799-4002-8.
Abstract | Links | BibTeX | Tags: Data Mining, Opinion Mining, Semantic Computing, Sentiment Analysis
@inproceedings{terranaAutomaticUnsupervisedPolarity2014,
title = {Automatic Unsupervised Polarity Detection on a Twitter Data Stream},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2014.17},
isbn = {978-1-4799-4002-8},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014},
pages = {128--134},
publisher = {IEEE Computer Society},
abstract = {In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges. textcopyright 2014 IEEE.},
keywords = {Data Mining, Opinion Mining, Semantic Computing, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges. textcopyright 2014 IEEE.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
Facebook Users Relationships Analysis Based on Sentiment Classification Proceedings Article
In: Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014, pp. 290–296, IEEE Computer Society, 2014, ISBN: 978-1-4799-4002-8.
Abstract | Links | BibTeX | Tags: Facebook, Semantic Computing, Sentiment Analysis, User Profiling
@inproceedings{terranaFacebookUsersRelationships2014,
title = {Facebook Users Relationships Analysis Based on Sentiment Classification},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2014.59},
isbn = {978-1-4799-4002-8},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014},
pages = {290--296},
publisher = {IEEE Computer Society},
abstract = {It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification. textcopyright 2014 IEEE.},
keywords = {Facebook, Semantic Computing, Sentiment Analysis, User Profiling},
pubstate = {published},
tppubtype = {inproceedings}
}
It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification. textcopyright 2014 IEEE.
2013
Augello, Agnese; Gaglio, Salvatore; Pilato, Giovanni; Vassallo, Giorgio
Clifford Rotors for Conceptual Representation in Chatbots Journal Article
In: Advances in Intelligent Systems and Computing, vol. 196 AISC, pp. 369–370, 2013, ISSN: 21945357.
Abstract | Links | BibTeX | Tags: Chatbots, Clifford algebra, Conceptual Spaces, Geometric algebra, Knowledge Representation, Latent Semantic Analysis, Natural Language Processing, Semantic Computing
@article{augelloCliffordRotorsConceptual2013,
title = {Clifford Rotors for Conceptual Representation in Chatbots},
author = { Agnese Augello and Salvatore Gaglio and Giovanni Pilato and Giorgio Vassallo},
doi = {10.1007/978-3-642-34274-5_64},
issn = {21945357},
year = {2013},
date = {2013-01-01},
journal = {Advances in Intelligent Systems and Computing},
volume = {196 AISC},
pages = {369--370},
abstract = {In this abstract we introduce an unsupervised sub-symbolic natural language sentences encoding procedure aimed at catching and representing into a Chatbot Knowledge Base (KB) the concepts expressed by an user interacting with a robot. The chatbot KB is coded in a conceptual space induced from the application of the Latent Semantic Analysis (LSA) paradigm on a corpus of documents. LSA has the effect of decomposing the original relationships between elements into linearly-independent vectors. Each basis vector can be considered therefore as a "conceptual coordinate", which can be tagged by the words which better characterize it. This tagging is obtained by performing a (TF-IDF)-like weighting schema [3], that we call TW-ICW (term weight-inverse conceptual coordinate weight), to weigh the relevance of each term on each conceptual coordinate. textcopyright 2013 Springer-Verlag.},
keywords = {Chatbots, Clifford algebra, Conceptual Spaces, Geometric algebra, Knowledge Representation, Latent Semantic Analysis, Natural Language Processing, Semantic Computing},
pubstate = {published},
tppubtype = {article}
}
In this abstract we introduce an unsupervised sub-symbolic natural language sentences encoding procedure aimed at catching and representing into a Chatbot Knowledge Base (KB) the concepts expressed by an user interacting with a robot. The chatbot KB is coded in a conceptual space induced from the application of the Latent Semantic Analysis (LSA) paradigm on a corpus of documents. LSA has the effect of decomposing the original relationships between elements into linearly-independent vectors. Each basis vector can be considered therefore as a "conceptual coordinate", which can be tagged by the words which better characterize it. This tagging is obtained by performing a (TF-IDF)-like weighting schema [3], that we call TW-ICW (term weight-inverse conceptual coordinate weight), to weigh the relevance of each term on each conceptual coordinate. textcopyright 2013 Springer-Verlag.
2012
Augello, Agnese; Pilato, Giovanni; Machi, Alberto; Gaglio, Salvatore
An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project Proceedings Article
In: Proceedings - IEEE 6th International Conference on Semantic Computing, ICSC 2012, pp. 186–193, 2012, ISBN: 978-0-7695-4859-3.
Abstract | Links | BibTeX | Tags: Artificial intelligence, Human computer interaction, Ontologies, Semantic Computing
@inproceedings{augelloApproachEnhanceChatbot2012,
title = {An Approach to Enhance Chatbot Semantic Power and Maintainability: Experiences within the FRASI Project},
author = { Agnese Augello and Giovanni Pilato and Alberto Machi and Salvatore Gaglio},
doi = {10.1109/ICSC.2012.26},
isbn = {978-0-7695-4859-3},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings - IEEE 6th International Conference on Semantic Computing, ICSC 2012},
pages = {186--193},
abstract = {The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules). textcopyright 2012 IEEE.},
keywords = {Artificial intelligence, Human computer interaction, Ontologies, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper illustrates the implementation and semantic enhancement of a domain-oriented Question-Answering system based on a pattern-matching chat bot technology, developed within an industrial project, named FRASI. The main difficulty in building a KB for a chat bot is to handwrite all possible question-answer pairs that constitute the KB. The proposed approach simplifies the chat bot realization thanks to two solutions. The first one uses an ontology, which is exploited in a twofold manner: to construct dynamic answers as a result of an inference process about the domain, and to automatically populate, off-line, the chat bot KB with sentences that can be derived from the ontology, describing properties and relations between concepts involved in the dialogue. The second one is to preprocess user sentences, and to reduce them to a simpler structure that can be referred to existing elements of the chat bot KB. The enhanced symbolic reduction of user questions and the automatic population of question templates in the chat bot KB from domain ontology have been implemented as two computational services (external modules). textcopyright 2012 IEEE.
Augello, Agnese; Gentile, Manuel; Pilato, Giovanni; Vassallo, Giorgio
Geometric Encoding of Sentences Based on Clifford Algebra Proceedings Article
In: KDIR 2012 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, pp. 457–462, 2012, ISBN: 978-989-8565-29-7.
Abstract | BibTeX | Tags: Geometric algebra, Information Retrieval, Knowledge Representation, Natural Language Processing, Semantic Computing, Semantic Spaces
@inproceedings{augelloGeometricEncodingSentences2012,
title = {Geometric Encoding of Sentences Based on Clifford Algebra},
author = { Agnese Augello and Manuel Gentile and Giovanni Pilato and Giorgio Vassallo},
isbn = {978-989-8565-29-7},
year = {2012},
date = {2012-01-01},
booktitle = {KDIR 2012 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval},
pages = {457--462},
abstract = {Natural language sentences can be represented as vectors in a high dimensional vector space. Generally, these models are based on bag of words approaches, and therefore they do not fully capture the semantics of sentences which depends both by the semantics of the words, and their order in in the phrase. In this work we propose a sub-symbolic methodology to encode natural language sentences considering both these two aspects. The proposed approach exploits the properties of Geometric Algebra rotation operators, called rotors, to code sentences through the rotation of an orthogonal basis of a semantic space. The methodology is based on three main steps: the construction of a semantic space, the association of ad-hoc rotors to sentence bigrams, and finally the coding of the sentence through the application of the obtained rotors to a standard basis in the semantic space. Copyright textcopyright 2012 SciTePress - Science and Technology Publications.},
keywords = {Geometric algebra, Information Retrieval, Knowledge Representation, Natural Language Processing, Semantic Computing, Semantic Spaces},
pubstate = {published},
tppubtype = {inproceedings}
}
Natural language sentences can be represented as vectors in a high dimensional vector space. Generally, these models are based on bag of words approaches, and therefore they do not fully capture the semantics of sentences which depends both by the semantics of the words, and their order in in the phrase. In this work we propose a sub-symbolic methodology to encode natural language sentences considering both these two aspects. The proposed approach exploits the properties of Geometric Algebra rotation operators, called rotors, to code sentences through the rotation of an orthogonal basis of a semantic space. The methodology is based on three main steps: the construction of a semantic space, the association of ad-hoc rotors to sentence bigrams, and finally the coding of the sentence through the application of the obtained rotors to a standard basis in the semantic space. Copyright textcopyright 2012 SciTePress - Science and Technology Publications.
Pilato, Giovanni; Augello, Agnese; Missikoff, Michele; Taglino, Francesco
Integration of Ontologies and Bayesian Networks for Maritime Situation Awareness Proceedings Article
In: Proceedings - IEEE 6th International Conference on Semantic Computing, ICSC 2012, pp. 170–177, 2012, ISBN: 978-0-7695-4859-3.
Abstract | Links | BibTeX | Tags: Context awareness, Ontologies, Semantic Computing
@inproceedings{pilatoIntegrationOntologiesBayesian2012,
title = {Integration of Ontologies and Bayesian Networks for Maritime Situation Awareness},
author = { Giovanni Pilato and Agnese Augello and Michele Missikoff and Francesco Taglino},
doi = {10.1109/ICSC.2012.25},
isbn = {978-0-7695-4859-3},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings - IEEE 6th International Conference on Semantic Computing, ICSC 2012},
pages = {170--177},
abstract = {This paper describes the main lines of the Intelligent Maritime Awareness Situation System (IMASS) developed to support an Electronic Surveillance platform conceived to contrast pirates activities in the Aden Gulf. The proposal is based on a solution that integrates an ontological approach in the description of the observed reality and a Bayesian approach to represent the experience and the knowledge of the domain experts. The intelligent system has been developed at a prototypical stage and tested with a complex scenario created with a simulator. The results are encouraging and indicate that this is a promising direction to go. textcopyright 2012 IEEE.},
keywords = {Context awareness, Ontologies, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper describes the main lines of the Intelligent Maritime Awareness Situation System (IMASS) developed to support an Electronic Surveillance platform conceived to contrast pirates activities in the Aden Gulf. The proposal is based on a solution that integrates an ontological approach in the description of the observed reality and a Bayesian approach to represent the experience and the knowledge of the domain experts. The intelligent system has been developed at a prototypical stage and tested with a complex scenario created with a simulator. The results are encouraging and indicate that this is a promising direction to go. textcopyright 2012 IEEE.
2011
Augello, Agnese; Scriminaci, Mario; Gaglio, Salvatore; Pilato, Giovanni
A Modular Framework for Versatile Conversational Agent Building Proceedings Article
In: Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2011, pp. 577–582, 2011, ISBN: 978-0-7695-4373-4.
Abstract | Links | BibTeX | Tags: Conversational Agents, Intelligent Agents, Knowledge Representation, Ontologies, Semantic Computing, Semantic Spaces
@inproceedings{augelloModularFrameworkVersatile2011,
title = {A Modular Framework for Versatile Conversational Agent Building},
author = { Agnese Augello and Mario Scriminaci and Salvatore Gaglio and Giovanni Pilato},
doi = {10.1109/CISIS.2011.95},
isbn = {978-0-7695-4373-4},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2011},
pages = {577--582},
abstract = {This paper illustrates a web-based infrastructure of an architecture for conversational agents equipped with a modular knowledge base. This solution has the advantage to allow the building of specific modules that deal with particular features of a conversation (ranging from its topic to the manner of reasoning of the chatbot). This enhances the agent interaction capabilities. The approach simplifies the chatbot knowledge base design process: extending, generalizing or even restricting the chatbot knowledge base in order to suit it to manage specific dialoguing tasks as much as possible. textcopyright 2011 IEEE.},
keywords = {Conversational Agents, Intelligent Agents, Knowledge Representation, Ontologies, Semantic Computing, Semantic Spaces},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper illustrates a web-based infrastructure of an architecture for conversational agents equipped with a modular knowledge base. This solution has the advantage to allow the building of specific modules that deal with particular features of a conversation (ranging from its topic to the manner of reasoning of the chatbot). This enhances the agent interaction capabilities. The approach simplifies the chatbot knowledge base design process: extending, generalizing or even restricting the chatbot knowledge base in order to suit it to manage specific dialoguing tasks as much as possible. textcopyright 2011 IEEE.
Pilato, Giovanni; Augello, Agnese; Gaglio, Salvatore
A Modular Architecture for Adaptive ChatBots Proceedings Article
In: Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011, pp. 177–180, 2011, ISBN: 978-0-7695-4492-2.
Abstract | Links | BibTeX | Tags: Chatbots, Conversational Agents, Intelligent Agents, Knowledge Representation, Semantic Computing
@inproceedings{pilatoModularArchitectureAdaptive2011,
title = {A Modular Architecture for Adaptive ChatBots},
author = { Giovanni Pilato and Agnese Augello and Salvatore Gaglio},
doi = {10.1109/ICSC.2011.68},
isbn = {978-0-7695-4492-2},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011},
pages = {177--180},
abstract = {We illustrate an architecture for a conversational agent based on a modular knowledge representation. This solution provides intelligent conversational agents with a dynamic and flexible behavior. The modularity of the architecture allows a concurrent and synergic use of different techniques, making it possible to use the most adequate methodology for the management of a specific characteristic of the domain, of the dialogue, or of the user behavior. We show the implementation of a proof-of-concept prototype: a set of modules exploiting different knowledge representation techniques and capable to differently manage conversation features has been developed. Each module is automatically triggered through a component, named corpus callosum, whose task is to choose, time by time, the most adequate chatbot knowledge section to activate. textcopyright 2011 IEEE.},
keywords = {Chatbots, Conversational Agents, Intelligent Agents, Knowledge Representation, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
We illustrate an architecture for a conversational agent based on a modular knowledge representation. This solution provides intelligent conversational agents with a dynamic and flexible behavior. The modularity of the architecture allows a concurrent and synergic use of different techniques, making it possible to use the most adequate methodology for the management of a specific characteristic of the domain, of the dialogue, or of the user behavior. We show the implementation of a proof-of-concept prototype: a set of modules exploiting different knowledge representation techniques and capable to differently manage conversation features has been developed. Each module is automatically triggered through a component, named corpus callosum, whose task is to choose, time by time, the most adequate chatbot knowledge section to activate. textcopyright 2011 IEEE.
Pilato, Giovanni; Augello, Agnese; Gaglio, Salvatore
Modular Knowledge Representation in Advisor Agents for Situation Awareness Journal Article
In: International Journal of Semantic Computing, vol. 5, no. 1, pp. 33–53, 2011, ISSN: 1793351X.
Abstract | Links | BibTeX | Tags: Chatbots, Context awareness, Conversational Agents, Decision Support Systems, Knowledge Representation, Semantic Computing
@article{pilatoModularKnowledgeRepresentation2011,
title = {Modular Knowledge Representation in Advisor Agents for Situation Awareness},
author = { Giovanni Pilato and Agnese Augello and Salvatore Gaglio},
doi = {10.1142/S1793351X11001158},
issn = {1793351X},
year = {2011},
date = {2011-01-01},
journal = {International Journal of Semantic Computing},
volume = {5},
number = {1},
pages = {33--53},
abstract = {A modular knowledge representation framework for conversational agents is presented. The approach has been realized to suit the situation awareness paradigm. The modularity of the framework makes possible the composition of specific modules that deal with particular features, simplifying both the chatbot design process and its smartness. As a proof of concepts we have developed a modular, situation awareness oriented, KB for a conversational agent, which plays the role of an advisor aimed at helping a user to be in charge of a virtual town, inspired to the SimCity series game. The agent makes an extensive use of semantic computing techniques and is able to perceive, comprehend and project consequences of actions in order to handle strategic decision under uncertainty conditions. textcopyright 2011 World Scientific Publishing Company.},
keywords = {Chatbots, Context awareness, Conversational Agents, Decision Support Systems, Knowledge Representation, Semantic Computing},
pubstate = {published},
tppubtype = {article}
}
A modular knowledge representation framework for conversational agents is presented. The approach has been realized to suit the situation awareness paradigm. The modularity of the framework makes possible the composition of specific modules that deal with particular features, simplifying both the chatbot design process and its smartness. As a proof of concepts we have developed a modular, situation awareness oriented, KB for a conversational agent, which plays the role of an advisor aimed at helping a user to be in charge of a virtual town, inspired to the SimCity series game. The agent makes an extensive use of semantic computing techniques and is able to perceive, comprehend and project consequences of actions in order to handle strategic decision under uncertainty conditions. textcopyright 2011 World Scientific Publishing Company.
2009
Augello, Agnese; Pilato, Giovanni; Gaglio, Salvatore
A Conversational Agent to Support Decisions in SimCity like Games Proceedings Article
In: ICSC 2009 - 2009 IEEE International Conference on Semantic Computing, pp. 367–372, 2009, ISBN: 978-0-7695-3800-6.
Abstract | Links | BibTeX | Tags: Artificial intelligence, Conversational Agents, Decision Support Systems, Human computer interaction, Semantic Computing
@inproceedings{augelloConversationalAgentSupport2009,
title = {A Conversational Agent to Support Decisions in SimCity like Games},
author = { Agnese Augello and Giovanni Pilato and Salvatore Gaglio},
doi = {10.1109/ICSC.2009.74},
isbn = {978-0-7695-3800-6},
year = {2009},
date = {2009-01-01},
booktitle = {ICSC 2009 - 2009 IEEE International Conference on Semantic Computing},
pages = {367--372},
abstract = {Computational intelligent techniques applied to economics have played an important role in the last years. In this paper we propose a framework based on an intelligent conversational agent embedded with a decision support system, aimed at suggesting the best managing strategies for a game-based model of a virtual town. The agent tries to prospect the future evolutions of particular choices taken by the user. Interaction is conducted through a natural language interface built as an Alice-based conversational agent. textcopyright 2009 IEEE.},
keywords = {Artificial intelligence, Conversational Agents, Decision Support Systems, Human computer interaction, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
Computational intelligent techniques applied to economics have played an important role in the last years. In this paper we propose a framework based on an intelligent conversational agent embedded with a decision support system, aimed at suggesting the best managing strategies for a game-based model of a virtual town. The agent tries to prospect the future evolutions of particular choices taken by the user. Interaction is conducted through a natural language interface built as an Alice-based conversational agent. textcopyright 2009 IEEE.
Augello, Agnese; Vassallo, Giorgio; Gaglio, Salvatore; Pilato, Giovanni
A Semantic Layer on Semi-Structured Data Sources for Intuitive Chatbots Proceedings Article
In: Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009, pp. 760–765, 2009, ISBN: 978-0-7695-3575-3.
Abstract | Links | BibTeX | Tags: Chatbots, Knowledge Representation, Natural Language Processing, Semantic Computing, Semantic Spaces
@inproceedings{augelloSemanticLayerSemistructured2009,
title = {A Semantic Layer on Semi-Structured Data Sources for Intuitive Chatbots},
author = { Agnese Augello and Giorgio Vassallo and Salvatore Gaglio and Giovanni Pilato},
doi = {10.1109/CISIS.2009.165},
isbn = {978-0-7695-3575-3},
year = {2009},
date = {2009-01-01},
booktitle = {Proceedings of the International Conference on Complex, Intelligent and Software Intensive Systems, CISIS 2009},
pages = {760--765},
abstract = {The main limits of chatbot technology are related to the building of their knowledge representation and to their rigid information retrieval and dialogue capabilities, usually based on simple "pattern matching rules". The analysis of distributional properties of words in a texts corpus allows the creation of semantic spaces where represent and compare natural language elements. This space can be interpreted as a "conceptual" space where the axes represent the latent primitive concepts of the analyzed corpus. The presented work aims at exploiting the properties of a data-driven semantic/conceptual space built using semistructured data sources freely available on the web, like Wikipedia. This coding is equivalent to adding, into the Wikipedia graph, a conceptual similarity relationship layer. The chatbot can exploit this layer in order to simulate an "intuitive" behavior, attempting to retrieve semantic relations between Wikipedia resources also through associative sub-symbolic paths. textcopyright 2009 IEEE.},
keywords = {Chatbots, Knowledge Representation, Natural Language Processing, Semantic Computing, Semantic Spaces},
pubstate = {published},
tppubtype = {inproceedings}
}
The main limits of chatbot technology are related to the building of their knowledge representation and to their rigid information retrieval and dialogue capabilities, usually based on simple "pattern matching rules". The analysis of distributional properties of words in a texts corpus allows the creation of semantic spaces where represent and compare natural language elements. This space can be interpreted as a "conceptual" space where the axes represent the latent primitive concepts of the analyzed corpus. The presented work aims at exploiting the properties of a data-driven semantic/conceptual space built using semistructured data sources freely available on the web, like Wikipedia. This coding is equivalent to adding, into the Wikipedia graph, a conceptual similarity relationship layer. The chatbot can exploit this layer in order to simulate an "intuitive" behavior, attempting to retrieve semantic relations between Wikipedia resources also through associative sub-symbolic paths. textcopyright 2009 IEEE.
2008
Augello, Agnese; Vassallo, Giorgio; Gaglio, Salvatore; Pilato, Giovanni
Sentence Induced Transformations in "Conceptual" Spaces Proceedings Article
In: Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008, pp. 34–41, 2008, ISBN: 978-0-7695-3279-0.
Abstract | Links | BibTeX | Tags: Clifford algebra, Geometric algebra, Latent Semantic Analysis, Natural Language Processing, Semantic Computing
@inproceedings{augelloSentenceInducedTransformations2008,
title = {Sentence Induced Transformations in "Conceptual" Spaces},
author = { Agnese Augello and Giorgio Vassallo and Salvatore Gaglio and Giovanni Pilato},
doi = {10.1109/ICSC.2008.74},
isbn = {978-0-7695-3279-0},
year = {2008},
date = {2008-01-01},
booktitle = {Proceedings - IEEE International Conference on Semantic Computing 2008, ICSC 2008},
pages = {34--41},
abstract = {The proposed work illustrates how "primitive concepts "can be automatically induced from a text corpus. The primitive concepts are identified by the orthonormal axis of a "conceptual" space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the "conceptual" space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geometric Algebra rotors, allow to highlight "conceptual" relations that can arise among the primitive concepts. textcopyright 2008 IEEE.},
keywords = {Clifford algebra, Geometric algebra, Latent Semantic Analysis, Natural Language Processing, Semantic Computing},
pubstate = {published},
tppubtype = {inproceedings}
}
The proposed work illustrates how "primitive concepts "can be automatically induced from a text corpus. The primitive concepts are identified by the orthonormal axis of a "conceptual" space induced by a methodology inspired to the Latent Semantic Analysis approach. The methodology represents a natural language sentence by means of a set of rotations of an orthonormal basis in the "conceptual" space. The rotations, triggered by the sequence of words composing the sentence and realized by means of Geometric Algebra rotors, allow to highlight "conceptual" relations that can arise among the primitive concepts. textcopyright 2008 IEEE.