- Αρχική
- Δημοσιεύσεις
- Δημοσιεύσεις
Δημοσιεύσεις
2008 |
Enhancing Library Services with Web 2.0 functionalities (Paper in Conference Proceedings) Gavrilis, Dimitris; Kakali,; Papatheodorou, Christos Research and Advanced Technology for Digital Libraries. 12th European Conference, ECDL 2008, Aarhus, Denmark, September 14-19, 2008. Proceedings, Volume: 5173 of the series Lecture Notes in Computer Science Pages: 148-159, Springer Berlin Heidelberg, 2008. @inproceedings{Gavrilis2008b, title = {Enhancing Library Services with Web 2.0 functionalities}, author = {Dimitris Gavrilis and Kakali and Christos Papatheodorou}, url = {http://www.dcu.gr/wp-content/uploads/2016/10/Enhancing-Library-Services-with-Web-2.0-functionalities.pdf}, year = {2008}, date = {2008-01-01}, booktitle = {Research and Advanced Technology for Digital Libraries. 12th European Conference, ECDL 2008, Aarhus, Denmark, September 14-19, 2008. Proceedings}, volume = {5173}, pages = {148-159}, publisher = {Springer Berlin Heidelberg}, series = {Lecture Notes in Computer Science}, abstract = {In this paper, a prototype of an Online Public Access Catalog (OPAC) is presented. This new OPAC features new functionalities and utilizes web 2.0 technologies in order to deliver improved search and retrieval services. Some of these new services include social tag annotations, user opinions and ranks and tag-based similarity searches. The prototype is evaluated by a user group through questionnaires, interviews and with the system's integrated logging mechanism. The results are encouraging enough and show that Library 2.0 technologies seem to be acceptable by the majority of the users. }, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this paper, a prototype of an Online Public Access Catalog (OPAC) is presented. This new OPAC features new functionalities and utilizes web 2.0 technologies in order to deliver improved search and retrieval services. Some of these new services include social tag annotations, user opinions and ranks and tag-based similarity searches. The prototype is evaluated by a user group through questionnaires, interviews and with the system's integrated logging mechanism. The results are encouraging enough and show that Library 2.0 technologies seem to be acceptable by the majority of the users. |
NaturalOWL: Generating Texts from OWL Ontologies in Protégé and in Second Life (Presentation) Karakatsiotis, George; Galanis, Dimitrios; Androutsopoulos, Ion Demonstration presented at the 18th European Conference on Artificial Intelligence , 2008. @misc{Karakatsiotis2008, title = {NaturalOWL: Generating Texts from OWL Ontologies in Protégé and in Second Life}, author = {George Karakatsiotis and Dimitrios Galanis and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/ecai2008_naturalowl.pdf}, year = {2008}, date = {2008-01-01}, abstract = {NaturalOWL is an open-source natural language generation engine written in Java. It produces descriptions of individuals (e.g., items for sale, museum exhibits) and classes (e.g., types of exhibits) in English and Greek from OWL DL ontologies. The ontologies must have been annotated in RDF with linguistic and user modeling resources. We demonstrate a plug-in for Protégé that can be used to produce these resources and to generate texts by invoking NaturalOWL. We also demonstrate how NaturalOWL can be used by robotic avatars in Second Life to describe the exhibits of virtual museums. NaturalOWL demonstrates the benefits of Natural Language Generation (NLG) on the Semantic Web. Organizations that need to publish information about objects, such as exhibits or products, can publish OWL ontologies instead of texts. NLG engines, embedded in browsers or Web servers, can then render the ontologies in multiple natural languages, whereas computer programs may access the ontologies directly. }, howpublished = {Demonstration presented at the 18th European Conference on Artificial Intelligence}, keywords = {}, pubstate = {published}, tppubtype = {presentation} } NaturalOWL is an open-source natural language generation engine written in Java. It produces descriptions of individuals (e.g., items for sale, museum exhibits) and classes (e.g., types of exhibits) in English and Greek from OWL DL ontologies. The ontologies must have been annotated in RDF with linguistic and user modeling resources. We demonstrate a plug-in for Protégé that can be used to produce these resources and to generate texts by invoking NaturalOWL. We also demonstrate how NaturalOWL can be used by robotic avatars in Second Life to describe the exhibits of virtual museums. NaturalOWL demonstrates the benefits of Natural Language Generation (NLG) on the Semantic Web. Organizations that need to publish information about objects, such as exhibits or products, can publish OWL ontologies instead of texts. NLG engines, embedded in browsers or Web servers, can then render the ontologies in multiple natural languages, whereas computer programs may access the ontologies directly. |
A Conversant Robotic Guide to Art Collections (Paper in Conference Proceedings) Vogiatzis, Dimitrios; Galanis, Dimitrios; Karkaletsis, Vangelis; Androutsopoulos, Ion; Spyropoulos, Constantine Proceedings of the 2nd Workshop on Language Technology for Cultural Heritage Data, Language Resources and Evaluation Conference (LREC 2008), 2008. @inproceedings{Vogiatzis2008, title = {A Conversant Robotic Guide to Art Collections}, author = {Dimitrios Vogiatzis and Dimitrios Galanis and Vangelis Karkaletsis and Ion Androutsopoulos and Constantine D. Spyropoulos }, url = {http://www.dcu.gr/wp-content/uploads/2016/10/A-Conversant-Robotic-Guide-to-Art-Collections.pdf}, year = {2008}, date = {2008-01-01}, booktitle = {Proceedings of the 2nd Workshop on Language Technology for Cultural Heritage Data, Language Resources and Evaluation Conference (LREC 2008)}, abstract = {We present the dialogue system of a robot that has been developed to serve as a museum guide. The robot interacts with human visitors in natural language, receiving instructions and providing information about the exhibits. Moreover, being mobile, it physically approaches the exhibits it provides information about. Although the robotic platform contains many modules, including navigation, speech recognition and synthesis, our focus in this paper is the dialogue system, which supports the sessions between humans and the robot, as well as the natural language generation engine, which generates the text to be spoken. Both modules are closely intertwined and depend on an ontology represented in OWL. The robot supports dialogues in both English and Greek. }, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present the dialogue system of a robot that has been developed to serve as a museum guide. The robot interacts with human visitors in natural language, receiving instructions and providing information about the exhibits. Moreover, being mobile, it physically approaches the exhibits it provides information about. Although the robotic platform contains many modules, including navigation, speech recognition and synthesis, our focus in this paper is the dialogue system, which supports the sessions between humans and the robot, as well as the natural language generation engine, which generates the text to be spoken. Both modules are closely intertwined and depend on an ontology represented in OWL. The robot supports dialogues in both English and Greek. |
2007 |
Integrating Dublin Core Metadata for Cultural Heritage Collections Using Ontologies (Paper in Conference Proceedings) Kakali,; Lourdi, Irini; Stasinopoulou,; Bountouri,; Papatheodorou, Christos; Doerr, Martin; Gergatsoulis, Proceedings of the 7th International Conference on Dublin Core and Metadata Applications, DC-2007, Pages: 128-139, 2007. @inproceedings{Kakali2007, title = {Integrating Dublin Core Metadata for Cultural Heritage Collections Using Ontologies}, author = {Kakali and Irini Lourdi and Stasinopoulou and Bountouri and Christos Papatheodorou and Martin Doerr and Gergatsoulis}, url = {http://eprints.rclis.org/11001/}, year = {2007}, date = {2007-08-01}, booktitle = {Proceedings of the 7th International Conference on Dublin Core and Metadata Applications, DC-2007}, pages = {128-139}, abstract = {Metadata interoperability is an active research area, especially for cultural heritage collections, which consist of heterogeneous objects described by a variety of metadata schemas. In this paper we propose an ontology-based metadata interoperability approach, which exploits, in an optimal way, the semantics of metadata schemas. In particular, we propose the use of CIDOC/CRM ontology as a mediating schema and present a methodology for mapping DC Type Vocabulary to CIDOC/CRM, demonstrating a real-world effort for ontology-based metadata integration.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Metadata interoperability is an active research area, especially for cultural heritage collections, which consist of heterogeneous objects described by a variety of metadata schemas. In this paper we propose an ontology-based metadata interoperability approach, which exploits, in an optimal way, the semantics of metadata schemas. In particular, we propose the use of CIDOC/CRM ontology as a mediating schema and present a methodology for mapping DC Type Vocabulary to CIDOC/CRM, demonstrating a real-world effort for ontology-based metadata integration. |
Learning Textual Entailment using SVMs and String Similarity Measures (Paper in Conference Proceedings) Malakasiotis, Prodromos; Androutsopoulos, Ion Proceedings of the Workshop on Textual Entailment and Paraphrasing, 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007), Pages: 42-47, 2007. @inproceedings{Malakasiotis2007, title = {Learning Textual Entailment using SVMs and String Similarity Measures}, author = {Prodromos Malakasiotis and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/rte3_paper.pdf}, year = {2007}, date = {2007-06-01}, booktitle = {Proceedings of the Workshop on Textual Entailment and Paraphrasing, 45th Annual Meeting of the Association for Computational Linguistics (ACL 2007)}, pages = {42-47}, abstract = {We present the system that we submitted to the 3rd Pascal Recognizing Textual Entailment Challenge. It uses four Support Vector Machines, one for each subtask of the challenge, with features that correspond to string similarity measures operating at the lexical and shallow syntactic level.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present the system that we submitted to the 3rd Pascal Recognizing Textual Entailment Challenge. It uses four Support Vector Machines, one for each subtask of the challenge, with features that correspond to string similarity measures operating at the lexical and shallow syntactic level. |
A multi-layer metadata schema for digital folklore collections (Journal Article) Lourdi, Irene; Papatheodorou, Christos; Nikolaidou, Mara Journal of Information Science, Volume: 33 (2), Pages: 197-213, 2007. @article{Lourdi2007, title = {A multi-layer metadata schema for digital folklore collections}, author = {Irene Lourdi and Christos Papatheodorou and Mara Nikolaidou}, url = {http://jis.sagepub.com/cgi/content/abstract/33/2/197}, year = {2007}, date = {2007-01-02}, journal = {Journal of Information Science}, volume = {33}, number = {2}, pages = {197-213}, abstract = {Digital folklore collections are valuable sources for studying the cultural and oral tradition of a country. The main difficulty in managing such collections is material heterogeneity (handwritten texts, photographs, 3D objects, sound recordings etc.) that imposes different digitization, description and maintenance practices. A multi-layer metadata model for the description of a digital folklore collection is presented. The proposed meta-data policy considers a collection as a hierarchy of entities and combines different metadata schemas for the management of each entity. The metadata model integrates elements from different metadata schemas ensuring efficient information recovery from all structural levels. Furthermore, interoperability between the used metadata schemas is discussed and a Topic Maps model is presented as an approach for developing mappings.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Digital folklore collections are valuable sources for studying the cultural and oral tradition of a country. The main difficulty in managing such collections is material heterogeneity (handwritten texts, photographs, 3D objects, sound recordings etc.) that imposes different digitization, description and maintenance practices. A multi-layer metadata model for the description of a digital folklore collection is presented. The proposed meta-data policy considers a collection as a hierarchy of entities and combines different metadata schemas for the management of each entity. The metadata model integrates elements from different metadata schemas ensuring efficient information recovery from all structural levels. Furthermore, interoperability between the used metadata schemas is discussed and a Topic Maps model is presented as an approach for developing mappings. |
Named Entity Recognition in Greek Texts with an Ensemble of SVMs and Active Learning (Journal Article) Lucarreli, Giorgios; Vasilakos, Xenofon; Androutsopoulos, Ion International Journal on Artificial Intelligence Tools (IJAIT), Volume: 16 (6), Pages: 1015 - 1045, 2007. @article{Lucarreli2007, title = {Named Entity Recognition in Greek Texts with an Ensemble of SVMs and Active Learning}, author = {Giorgios Lucarreli and Xenofon Vasilakos and Ion Androutsopoulos}, url = {http://db0.worldscinet.com/worldsci-staging/detail.nsp}, year = {2007}, date = {2007-01-01}, journal = {International Journal on Artificial Intelligence Tools (IJAIT)}, volume = {16}, number = {6}, pages = {1015 - 1045}, abstract = {We present a freely available named-entity recognizer for Greek texts that identifies temporal expressions, person, and organization names. For temporal expressions, it relies on semi-automatically produced patterns. For person and organization names, it employs an ensemble of Support Vector Machines that scan the input text in two passes. The ensemble is trained using active learning, whereby the system itself proposes candidate training instances to be annotated by a human during training. The recognizer was evaluated on both a general collection of newspaper articles and a more focussed, in terms of topics, collection of financial articles.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We present a freely available named-entity recognizer for Greek texts that identifies temporal expressions, person, and organization names. For temporal expressions, it relies on semi-automatically produced patterns. For person and organization names, it employs an ensemble of Support Vector Machines that scan the input text in two passes. The ensemble is trained using active learning, whereby the system itself proposes candidate training instances to be annotated by a human during training. The recognizer was evaluated on both a general collection of newspaper articles and a more focussed, in terms of topics, collection of financial articles. |
Ontology-based Metadata Integration in the Cultural Heritage Domain (Paper in Conference Proceedings) Stasinopoulou, Thomais; Bountouri, Lina; Lourdi, Irini; Papatheodorou, Christos; Doerr, Martin; Gergatsoulis, Manolis Proceedings of the 10th International Conference on Asian Digital Libraries, ICADL-2007, Hanoi, Vietnam, December 2007, Lecture Notes in Computer Science (LNCS), Volume: 4822/2007 Pages: 165-175, 2007. @inproceedings{Stasinopoulou2007, title = {Ontology-based Metadata Integration in the Cultural Heritage Domain}, author = {Thomais Stasinopoulou and Lina Bountouri and Irini Lourdi and Christos Papatheodorou and Martin Doerr and Manolis Gergatsoulis}, url = {http://www.springerlink.com/content/k252223528n55127/}, year = {2007}, date = {2007-01-01}, booktitle = {Proceedings of the 10th International Conference on Asian Digital Libraries, ICADL-2007, Hanoi, Vietnam, December 2007, Lecture Notes in Computer Science (LNCS)}, volume = {4822/2007}, pages = {165-175}, abstract = {In this paper, we propose an ontology-based metadata integration methodology for the cultural heritage domain. The proposed real - world approach considers an integration architecture in which CIDOC/CRM ontology acts as a mediating scheme. In this context, we present a mapping methodology from Encoded Archival Description (EAD) and Dublin Core (DC) metadata to CIDOC/CRM, and discuss the faced difficulties.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In this paper, we propose an ontology-based metadata integration methodology for the cultural heritage domain. The proposed real - world approach considers an integration architecture in which CIDOC/CRM ontology acts as a mediating scheme. In this context, we present a mapping methodology from Encoded Archival Description (EAD) and Dublin Core (DC) metadata to CIDOC/CRM, and discuss the faced difficulties. |
Generating Multilingual Descriptions from Linguistically Annotated OWL Ontologies: the NaturalOWL System (Paper in Conference Proceedings) Galanis, Dimitris; Androutsopoulos, Ion Proceedings of the 11th European Workshop on Natural Language Generation (ENLG 2007), Pages: 143-146, 2007. @inproceedings{Galanis2007, title = {Generating Multilingual Descriptions from Linguistically Annotated OWL Ontologies: the NaturalOWL System}, author = {Dimitris Galanis and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/naturalowl_enlg07.pdf}, year = {2007}, date = {2007-01-01}, booktitle = {Proceedings of the 11th European Workshop on Natural Language Generation (ENLG 2007)}, pages = {143-146}, abstract = {We introduce Naturalowl, an open-source multilingual natural language generator that produces descriptions of instances and classes, starting from a linguistically annotated ontology. The generator is heavily based on ideas from ilex and m-piro, but it is in many ways simpler and it provides full support for owl dl ontologies with rdf linguistic annotations. Naturalowl is written in Java, and it is supported by m-piro’s authoring tool, as well as an alternative plug-in for the Protégé ontology editor.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We introduce Naturalowl, an open-source multilingual natural language generator that produces descriptions of instances and classes, starting from a linguistically annotated ontology. The generator is heavily based on ideas from ilex and m-piro, but it is in many ways simpler and it provides full support for owl dl ontologies with rdf linguistic annotations. Naturalowl is written in Java, and it is supported by m-piro’s authoring tool, as well as an alternative plug-in for the Protégé ontology editor. |
Word Sense Disambiguation with Spreading Activation Networks Generated from Thesauri (Paper in Conference Proceedings) Tsatsaronis, George; Varzigiannis, Michalis; Androutsopoulos, Ion Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007), Pages: 1725-1730, 2007. @inproceedings{Tsatsaronis2007, title = {Word Sense Disambiguation with Spreading Activation Networks Generated from Thesauri}, author = {George Tsatsaronis and Michalis Varzigiannis and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/ijcai2007_wsd_paper.pdf}, year = {2007}, date = {2007-01-01}, booktitle = {Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007)}, pages = {1725-1730}, abstract = {Most word sense disambiguation (WSD) methods require large quantities of manually annotated training data and/or do not exploit fully the semantic relations of thesauri. We propose a new unsupervised WSD algorithm, which is based on generating Spreading Activation Networks (SANs) from the senses of a thesaurus and the relations between them. A new method of assigning weights to the networks’ links is also proposed. Experiments show that the algorithm outperforms previous unsupervised approaches to WSD.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Most word sense disambiguation (WSD) methods require large quantities of manually annotated training data and/or do not exploit fully the semantic relations of thesauri. We propose a new unsupervised WSD algorithm, which is based on generating Spreading Activation Networks (SANs) from the senses of a thesaurus and the relations between them. A new method of assigning weights to the networks’ links is also proposed. Experiments show that the algorithm outperforms previous unsupervised approaches to WSD. |
Η ψηφιακή επιμέλεια των πολιτισμικών συλλογών ως πεδίο γνώσης και πρακτικής (Paper in Conference Proceedings) Dallas, Costis Πρακτικά Ημερίδας της Ελληνικής Ομπσπονδίας Σωματείων Φίλων των Μουσείων (ΕΟΣΦΙΜ), 2007. @inproceedings{Dallas2007, title = {Η ψηφιακή επιμέλεια των πολιτισμικών συλλογών ως πεδίο γνώσης και πρακτικής}, author = {Costis Dallas}, url = {http://www.heritage-museums.com/gr/attachments/article/359/praktika.pdf}, year = {2007}, date = {2007-01-01}, booktitle = {Πρακτικά Ημερίδας της Ελληνικής Ομπσπονδίας Σωματείων Φίλων των Μουσείων (ΕΟΣΦΙΜ)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
2006 |
Analyzing and Evaluating Usefulness and Usability in Electronic Information Services (Journal Article) Tsakonas, Giannis; Papatheodorou, Christos Journal of Information Science , Volume: 32 (5), Pages: 400-419, 2006. @article{Tsakonas2006, title = {Analyzing and Evaluating Usefulness and Usability in Electronic Information Services}, author = {Giannis Tsakonas and Christos Papatheodorou}, url = {http://jis.sagepub.com/cgi/content/abstract/32/5/400}, year = {2006}, date = {2006-01-02}, journal = {Journal of Information Science }, volume = {32}, number = {5}, pages = {400-419}, abstract = {Digital libraries, e-journal platforms, portals, e-prints and other web-based information systems provide services supporting users to perform intense work tasks that require complex interaction activities. The main components of such services are the users, the offered content and the system on which they are performed. This paper presents a model, which analyses the attributes of the electronic information services' components that affect user interaction and correlates them in the usefulness and usability evaluation process. An experimental study traces the relations between usefulness and usability, indicating that these evaluation parameters are interconnected and users do not find discriminating differences between them. The analysis of the content and system attributes suggests that user interaction is affected equally by content and system characteristics. Finally, the study illustrates users' preference for the attributes that constitute a useful system in contrast to those that support usability.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Digital libraries, e-journal platforms, portals, e-prints and other web-based information systems provide services supporting users to perform intense work tasks that require complex interaction activities. The main components of such services are the users, the offered content and the system on which they are performed. This paper presents a model, which analyses the attributes of the electronic information services' components that affect user interaction and correlates them in the usefulness and usability evaluation process. An experimental study traces the relations between usefulness and usability, indicating that these evaluation parameters are interconnected and users do not find discriminating differences between them. The analysis of the content and system attributes suggests that user interaction is affected equally by content and system characteristics. Finally, the study illustrates users' preference for the attributes that constitute a useful system in contrast to those that support usability. |
Source authoring for multilingual generation of personalised object descriptions (Journal Article) Androutsopoulos, Ion; Oberlander, Jon; Karkaletsis, Vangelis Natural Language Engineering, Volume: 13 (3), Pages: 191-233, 2006. @article{Androutsopoulos2006, title = {Source authoring for multilingual generation of personalised object descriptions}, author = {Ion Androutsopoulos and Jon Oberlander and Vangelis Karkaletsis}, url = {http://www.aueb.gr/users/ion/docs/nle_mpiro.pdf}, year = {2006}, date = {2006-01-02}, journal = {Natural Language Engineering}, volume = {13}, number = {3}, pages = {191-233}, abstract = {We present the source authoring facilities of a natural language generation system that produces personalised descriptions of objects in multiple natural languages starting from language-independent symbolic information in ontologies and databases as well as pieces of canned text. The system has been tested in applications ranging from museum exhibitions to presentations of computer equipment for sale. We discuss the architecture of the overall system, the resources that the authors manipulate, the functionality of the authoring facilities, the system’s personalisation mechanisms, and how they relate to source authoring. A usability evaluation of the authoring facilities is also presented, followed by more recent work on reusing information extracted from existing databases and documents, and supporting the owl ontology specification language. }, keywords = {}, pubstate = {published}, tppubtype = {article} } We present the source authoring facilities of a natural language generation system that produces personalised descriptions of objects in multiple natural languages starting from language-independent symbolic information in ontologies and databases as well as pieces of canned text. The system has been tested in applications ranging from museum exhibitions to presentations of computer equipment for sale. We discuss the architecture of the overall system, the resources that the authors manipulate, the functionality of the authoring facilities, the system’s personalisation mechanisms, and how they relate to source authoring. A usability evaluation of the authoring facilities is also presented, followed by more recent work on reusing information extracted from existing databases and documents, and supporting the owl ontology specification language. |
A Greek Named-Entity Recognizer That Uses Support Vector Machines and Active Learning (Paper in Conference Proceedings) Lucarreli, Giorgos; Androutsopoulos, Ion Advances in Artificial Intelligence. 4th Hellenic Conference on Artificial Intelligence (SETN 2006). Proceedings, Volume: 3955 of the series Lecture Notes in Computer Science Pages: 203-213, 2006. @inproceedings{Lucarreli2006, title = {A Greek Named-Entity Recognizer That Uses Support Vector Machines and Active Learning}, author = {Giorgos Lucarreli and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/setn2006_paper.pdf}, year = {2006}, date = {2006-01-02}, booktitle = {Advances in Artificial Intelligence. 4th Hellenic Conference on Artificial Intelligence (SETN 2006). Proceedings}, volume = {3955}, pages = {203-213}, series = {Lecture Notes in Computer Science}, abstract = {We present a named-entity recognizer forGreek person names and temporal expressions. For temporal expressions, it relies on semiautomatically produced patterns. For person names, it employs two Support Vector Machines, that scan the input text in two passes, and active learning, which reduces the human annotation effort during training.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present a named-entity recognizer forGreek person names and temporal expressions. For temporal expressions, it relies on semiautomatically produced patterns. For person names, it employs two Support Vector Machines, that scan the input text in two passes, and active learning, which reduces the human annotation effort during training. |
2005 |
A Practically Unsupervised Learning Method to Identify Single-Snippet Answers to Definition Questions on theWeb (Paper in Conference Proceedings) Androutsopoulos, Ion; Galanis, Dimitris Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, of the series HLT '05 Pages: 323-330, Association for Computational Linguistics, 2005. @inproceedings{Androutsopoulos2005, title = {A Practically Unsupervised Learning Method to Identify Single-Snippet Answers to Definition Questions on theWeb}, author = {Ion Androutsopoulos and Dimitris Galanis}, url = {http://www.aueb.gr/users/ion/docs/hltemnlp2005_paper.pdf}, year = {2005}, date = {2005-01-03}, booktitle = {Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing}, pages = {323-330}, publisher = {Association for Computational Linguistics}, series = {HLT '05}, abstract = {We present a practically unsupervised learning method to produce single-snippet answers to definition questions in question answering systems that supplement Web search engines. The method exploits on-line encyclopedias and dictionaries to generate automatically an arbitrarily large number of positive and negative definition examples, which are then used to train an SVM to separate the two classes. We show experimentally that the proposed method is viable, that it outperforms the alternative of training the system on questions and news articles from TREC, and that it helps the search engine handle definition questions significantly better.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present a practically unsupervised learning method to produce single-snippet answers to definition questions in question answering systems that supplement Web search engines. The method exploits on-line encyclopedias and dictionaries to generate automatically an arbitrarily large number of positive and negative definition examples, which are then used to train an SVM to separate the two classes. We show experimentally that the proposed method is viable, that it outperforms the alternative of training the system on questions and news articles from TREC, and that it helps the search engine handle definition questions significantly better. |
2004 |
Learning to Identify Single-Snippet Answers to Definition Questions (Paper in Conference Proceedings) Miliaraki, Spyridoula; Androutsopoulos, Ion Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004), Pages: 1360-1366, 2004. @inproceedings{Miliaraki2004, title = {Learning to Identify Single-Snippet Answers to Definition Questions}, author = {Spyridoula Miliaraki and Ion Androutsopoulos}, url = {http://www.aueb.gr/users/ion/docs/coling04_definition_questions.pdf}, year = {2004}, date = {2004-01-01}, booktitle = {Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004)}, pages = {1360-1366}, abstract = {We present a learning-based method to identify single-snippet answers to definition questions in question answering systems for document collections. Our method combines and extends two previous techniques that were based mostly on manually crafted lexical patterns and WordNet hypernyms. We train a Support Vector Machine (SVM) on vectors comprising the verdicts or attributes of the previous techniques, and additional phrasal attributes that we acquire automatically. The SVM is then used to identify and rank single 250-character snippets that contain answers to definition questions. Experimental results indicate that our method clearly outperforms the techniques it builds upon.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } We present a learning-based method to identify single-snippet answers to definition questions in question answering systems for document collections. Our method combines and extends two previous techniques that were based mostly on manually crafted lexical patterns and WordNet hypernyms. We train a Support Vector Machine (SVM) on vectors comprising the verdicts or attributes of the previous techniques, and additional phrasal attributes that we acquire automatically. The SVM is then used to identify and rank single 250-character snippets that contain answers to definition questions. Experimental results indicate that our method clearly outperforms the techniques it builds upon. |
2003 |
Natural Language Interaction (Book Chapter) Androutsopoulos, Ion; Aretoulaki, Maria Mitkov, (Ed.): The Oxford Handbook of Computational Linguistics, Chapter 35, Pages: 629-649, Oxford University Press, 2003. @inbook{Androutsopoulos2003, title = {Natural Language Interaction}, author = {Ion Androutsopoulos and Maria Aretoulaki}, editor = {R. Mitkov}, url = {http://www.oxfordhandbooks.com/view/10.1093/oxfordhb/9780199276349.001.0001/oxfordhb-9780199276349-e-35}, doi = {10.1093/oxfordhb/9780199276349.013.0035}, year = {2003}, date = {2003-01-01}, booktitle = {The Oxford Handbook of Computational Linguistics}, pages = {629-649}, publisher = {Oxford University Press}, chapter = {35}, abstract = {This article introduces natural language interaction (NLI) systems. NLI systems are systems that allow their users to formulate requests in spoken or written natural language. This article highlights the central concepts of natural language interaction systems. NLI systems refer to applications where users can formulate requests addressed to a computer in natural language. Database querying constitutes the most studied form of NLIs. Database NLIs allow information to be retrieved from an underlying database by typing single-sentence queries. This article draws attention to the basic components of an NLI system and gives an overview of spoken dialogue systems (SDS). Apart from giving information about the several applications where NLIs and SDS are being explored, this article concludes with a discussion of more ambitious forms of natural language interaction that may become possible in the longer term.}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } This article introduces natural language interaction (NLI) systems. NLI systems are systems that allow their users to formulate requests in spoken or written natural language. This article highlights the central concepts of natural language interaction systems. NLI systems refer to applications where users can formulate requests addressed to a computer in natural language. Database querying constitutes the most studied form of NLIs. Database NLIs allow information to be retrieved from an underlying database by typing single-sentence queries. This article draws attention to the basic components of an NLI system and gives an overview of spoken dialogue systems (SDS). Apart from giving information about the several applications where NLIs and SDS are being explored, this article concludes with a discussion of more ambitious forms of natural language interaction that may become possible in the longer term. |
Speaking the Users’ Languages (Journal Article) Isard, Amy; Oberlander, Jon; Matheson, Colin; Androutsopoulos, Ion IEEE Intelligent Systems, Volume: 18 (1), Pages: 40-45, 2003. @article{Isard2003, title = {Speaking the Users’ Languages}, author = {Amy Isard and Jon Oberlander and Colin Matheson and Ion Androutsopoulos }, url = {http://www.aueb.gr/users/ion/docs/ieeeis_speaking_the_users_languages.pdf}, year = {2003}, date = {2003-01-01}, journal = {IEEE Intelligent Systems}, volume = {18}, number = {1}, pages = {40-45}, abstract = {The authors describe a system that generates descriptions of museum objects tailored to the user. The texts presented to adults, children, and experts differ in several ways, from the choice of words used to the complexity of the sentence forms.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The authors describe a system that generates descriptions of museum objects tailored to the user. The texts presented to adults, children, and experts differ in several ways, from the choice of words used to the complexity of the sentence forms. |
2002 |
Exploring Time, Tense and Aspect in Natural Language Database Interfaces (Book) Androutsopoulos, Ion John Benjamins Publishing Company, 2002, ISBN: 9789027249906. @book{Androutsopoulos2002, title = {Exploring Time, Tense and Aspect in Natural Language Database Interfaces}, author = {Ion Androutsopoulos}, url = {https://www.benjamins.com/#catalog/books/nlp.6/main}, doi = {10.1075/nlp.6}, isbn = {9789027249906}, year = {2002}, date = {2002-01-01}, publisher = {John Benjamins Publishing Company}, abstract = {Advances in temporal databases make it increasingly easier to store time-dependent information, creating a need for facilities that will help end-users access this information. In the context of natural language interaction, significant effort has been devoted to interfaces that allow database queries to be formulated in natural language. Most of the existing interfaces, however, do not support adequately the notion of time. Drawing upon tense and aspect theories, temporal logics, and temporal databases, this cross-discipline book examines relevant issues from the three areas, developing a unified theoretical framework that can be used to build natural language interfaces to temporal databases. The framework features an HPSG mapping from English to a formally defined meaning representation language, and a corresponding mapping to a temporal extension of the SQL database language. The book is accompanied by a freely available prototype interface, built according to the framework, and implemented using Prolog and ALE. This is the first in-depth exploration of the notion of time in natural language database interfaces. It will be particularly interesting to researchers working on natural language interaction, tense and aspect, HPSG, temporal logics, and temporal databases, especially those who wish to learn about time-related issues in other disciplines.}, keywords = {}, pubstate = {published}, tppubtype = {book} } Advances in temporal databases make it increasingly easier to store time-dependent information, creating a need for facilities that will help end-users access this information. In the context of natural language interaction, significant effort has been devoted to interfaces that allow database queries to be formulated in natural language. Most of the existing interfaces, however, do not support adequately the notion of time. Drawing upon tense and aspect theories, temporal logics, and temporal databases, this cross-discipline book examines relevant issues from the three areas, developing a unified theoretical framework that can be used to build natural language interfaces to temporal databases. The framework features an HPSG mapping from English to a formally defined meaning representation language, and a corresponding mapping to a temporal extension of the SQL database language. The book is accompanied by a freely available prototype interface, built according to the framework, and implemented using Prolog and ALE. This is the first in-depth exploration of the notion of time in natural language database interfaces. It will be particularly interesting to researchers working on natural language interaction, tense and aspect, HPSG, temporal logics, and temporal databases, especially those who wish to learn about time-related issues in other disciplines. |
2000 |
Database Interfaces (Book Chapter) Androutsopoulos, Ion; Ritchie, Graeme R. Dale H. Moisl,; Somers, (Ed.): Handbook of Natural Language Processing, Chapter 9, Pages: 209-240, Marcel Dekker Inc., 2000, ISBN: 0824790006. @inbook{Androutsopoulos2000, title = {Database Interfaces}, author = {Ion Androutsopoulos and Graeme Ritchie}, editor = {R. Dale, H. Moisl, and H. Somers}, url = {http://dl.acm.org/citation.cfm?id=555864}, isbn = {0824790006}, year = {2000}, date = {2000-01-01}, booktitle = {Handbook of Natural Language Processing}, pages = {209-240}, publisher = {Marcel Dekker Inc.}, chapter = {9}, keywords = {}, pubstate = {published}, tppubtype = {inbook} } |
