BibSonomyburst/user/diego_ma/AnswerFinderBibSonomy RSS feed for /user/diego_ma/AnswerFinder2012-02-16T21:35:05+01:00http://www.bibsonomy.org/bibtex/264e2ff61c23df0f5f02914ea091dc158/diego_madiego_ma2008-10-10T05:18:00+02:00named_entities AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, <a href="/author/van Zaanen">Menno van Zaanen</a>, and <a href="/author/Smith">Daniel Smith</a> </span><em>Proceedings ALTW 2006, </em><em>page 51-58. </em>(<em>2006</em>)Fri Oct 10 05:18:00 CEST 2008Proceedings ALTW 200651-58Named Entity Recognition for Question Answering2006named_entities AnswerFinder molla_publication Current text-based question answering (QA) systems usually contain a named entity recogniser (NER) as a core component. Named entity recognition as traditionally been developed as a component for information extraction systems, and current techniques are focused on this end use. However, no formal assessment has been done on the characteristics of a NER within the task of question answering. In this paper we present a NER that aims at higher recall by allowing multiple entity labels to strings. The NER is embedded in a question answering system and the overall QA system performance is compared to that of one with a traditional variation of the NER that only allows single entity labels. It is shown that the added noise produced introduced by the additional labels is offset by the higher recall gained, therefore enabling the QA system to have a better chance to find the answer.http://www.bibsonomy.org/bibtex/2cc132a9e1fda44b9f205512d8975952c/diego_madiego_ma2008-07-01T10:45:03+02:00question_answering molla_publication AnswerFinder inf_retrieval <span class="authorEditorList"><a href="/author/Pizzato">Luiz Pizzato</a>, and <a href="/author/Mollá">Diego Mollá</a> </span><em>Proc. COLING Workshop on Information Retrieval for Question Answering, </em><em>page 8 pages. </em>(<em>2008</em>)Tue Jul 01 10:45:03 CEST 2008Proc. COLING Workshop on Information Retrieval for Question Answering8 pagesIndexing on Semantic Roles for Question Answering2008question_answering molla_publication AnswerFinder inf_retrieval Semantic Role Labeling (SRL) has been used successfully in several stages of automated Question Answering (QA) systems but its inherent slow procedures make it difficult to use at the indexing stage of the document retrieval component. In this paper we confirm the intuition that SRL at indexing stage improves the performance of QA and propose a simplified technique named the Question Prediction Language Model (QPLM), which provides similar information with a much lower cost. The methods were tested on four different QA systems and the results suggest that QPLM can be used as a good compromise between speed and accuracy.http://www.bibsonomy.org/bibtex/25ddeca10bfa22885c0c1a6a429ae5ed9/diego_madiego_ma2008-03-04T07:47:41+01:00AnswerFinder inf_retrieval molla_publication <span class="authorEditorList"><a href="/author/Pizzato">Luiz Pizzato</a>, <a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Paris">Cécile Paris</a> </span><em>Proceedings ALTW, </em><em> 4, </em><em>page 83-90. </em>(<em>2006</em>)Tue Mar 04 07:47:41 CET 2008Proceedings ALTW83-90Pseudo Relevance Feedback Using Named Entities for Question Answering42006AnswerFinder inf_retrieval molla_publication Relevance feedback has already proven its usefulness in probabilistic information retrieval (IR). In this research we explore whether a pseudo relevance feedback technique on IR can improve the Question Answering task (QA). The basis of our exploration is the use of relevant named entities from the top retrieved documents as clues of relevance. We discuss two interesting findings from these experiments: the reasons the results were not improved, and the fact that today's metrics of IR evalu ation on QA do not reflect the results obtained by a QA system.http://www.bibsonomy.org/bibtex/2d2a43592b416f89978d82c5cd2e06ef7/diego_madiego_ma2008-03-04T07:46:51+01:00AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Gardiner">Mary Gardiner</a> </span><em>Proc. ALTW 2004, </em><em>page 9-16. </em><em>Sydney, Australia, </em><em>Macquarie University, </em>(<em>2004</em>)Tue Mar 04 07:46:51 CET 2008Sydney, AustraliaProc. ALTW 20049-16AnswerFinder - Question Answering by Combining Lexical, Syntactic and Semantic Information2004AnswerFinder molla_publication We present a question answering system that combines information at the lexical, syntactic, and semantic levels, in the process to find and rank the candidate answer sentences. The candidate exact answers are extracted from the candidate answer sentences by means of a combination of information-extraction techniques (named entity recognition) and patterns based on logical forms. The system participated in the question answering track of TREC 2004.http://www.bibsonomy.org/bibtex/2d3e298514ecd89ffb3bd1b5cb939e540/diego_madiego_ma2008-02-27T03:34:35+01:00AnswerFinder summarisation question_answering molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Wan">Stephen Wan</a> </span><em>Proceedings DUC, </em>(<em>2006</em>)Wed Feb 27 03:34:35 CET 2008Proceedings DUCMacquarie University at DUC 2006: Question Answering for Summarisation2006AnswerFinder summarisation question_answering molla_publication We present an approach to summarisation based on the use of a question answering system to select the most relevant sentences. We used AnswerFinder, a question answering system that is being developed at Macquarie University. The sentences returned by AnswerFinder are further re-ranked and collated to produce the final summary. This system will serve as a baseline upon which we intend to develop methods more specific to the task of question-driven summarisation.http://www.bibsonomy.org/bibtex/2d40066e489bb1545f2afc538c451b0b3/diego_madiego_ma2008-02-06T06:48:51+01:00graphs AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a> </span><em>Proc. HLT/NAACL 2006 Workshop on Graph Algorithms for Natural Language Processing, </em><em>page 37-44. </em>(<em>2006</em>)Wed Feb 06 06:48:51 CET 2008Proc. HLT/NAACL 2006 Workshop on Graph Algorithms for Natural Language Processing37-44Learning of Graph-based Question Answering Rules2006graphs AnswerFinder molla_publication In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences. Question answering rules are automatically learnt from a training corpus of questions and answer sentences with the answer annotated. The method is independent from the graph representation formalism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences.http://www.bibsonomy.org/bibtex/2a138fccaf668e2ac25eb12206aecad63/diego_madiego_ma2008-01-29T08:25:08+01:00AnswerFinder molla_publication Spanish <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a> </span><em>Procesamiento del Lenguaje Natural</em> (<em>2004</em>)Tue Jan 29 08:25:08 CET 2008Procesamiento del Lenguaje Natural17-24Hacia el Uso de la Informaci{\'o}n Sint{\'a}ctica y Sem{\'a}ntica en los Sistemas de B{\'u}squeda de Respuestas332004AnswerFinder molla_publication Spanish Current question answering systems typically combine methods based in information retrieval and information extraction. Such methods leverage the speed of the resulting algorithms and the presence of information redundancy, but few systems use methods based on linguistic information beyond the word level. In this paper we present a study of the impact of the syntactic and semantic information in the selection process of the final candidate sentence. The selection process is based on measures of grammatical relation overlap and flat logical form overlap.http://www.bibsonomy.org/bibtex/251a7573fde0a098e561c31f0d776ad5c/diego_madiego_ma2008-01-29T08:20:55+01:00AnswerFinder dependencies molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Hutchinson">Ben Hutchinson</a> </span><em>Proc. 2002 Australasian NLP Workshop, </em>(<em>2002</em>)Tue Jan 29 08:20:55 CET 2008Proc. 2002 Australasian NLP WorkshopDependency-based Semantic Interpretation for Answer Extraction2002AnswerFinder dependencies molla_publication http://www.bibsonomy.org/bibtex/2a9ae1ef031141fe460eaa6deea6036d7/diego_madiego_ma2008-01-29T08:19:28+01:00parsers evaluation AnswerFinder gram_rels molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Hutchinson">Ben Hutchinson</a> </span><em>Proc. European Association for Computational Linguistics EACL, workshop on Evaluation Initiatives in Natural Language Processing, </em><em>page 43-50. </em><em>Budapest, </em><em>Association for Computational Linguistics, </em><em>ACL, </em>(<em>April 2003</em>)Tue Jan 29 08:19:28 CET 2008BudapestProc. European Association for Computational Linguistics (EACL), workshop on Evaluation Initiatives in Natural Language ProcessingApril43-50Intrinsic versus Extrinsic Evaluations of Parsing Systems2003parsers evaluation AnswerFinder gram_rels molla_publication A wide range of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (intrinsic evaluations), and only in a few cases has the effect of different parsers in real applications been measured (extrinsic evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the intrinsic evaluation, the accuracy of the parsers is compared independently by converting the dependencies into grammatical relations and using the methodology of \newcite{Carroll:1998} for parser comparison. In the extrinsic evaluation, the parsers' impact in a practical application is compared within the context of answer extraction. The differences in the results are significant.http://www.bibsonomy.org/bibtex/2ddf167520fb423a651e0c5dcb062f1f2/diego_madiego_ma2008-01-29T08:16:55+01:00AnswerFinder parsers evaluation gram_rels molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Hutchinson">Ben Hutchinson</a> </span>(<em>2002</em>)<em>In preparation . </em>Tue Jan 29 08:16:55 CET 2008In preparationIn Vitro and In Vivo Evaluations of Parsing Systems Within the Context of Answer Extraction2002AnswerFinder parsers evaluation gram_rels molla_publication A wide variety of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (\emph{in vitro} evaluations), and only in a few cases has the effect of different parsers in real applications been measured (\emph{in vivo} evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the first evaluation, the accuracy of the parsers is compared \emph{in vitro} by converting the dependencies into grammatical relations and using the methodology of \newcite{Carroll:1998} for parser comparison. In the second evaluation, the parsers' impact in a practical application is compared \emph{in vivo} within the context of answer extraction. The differences in the results are significant and raise questions on the usefulness of purely \emph{in vitro} evaluations.http://www.bibsonomy.org/bibtex/239fce546c0e3de46c67db564b0767efe/diego_madiego_ma2008-01-29T08:07:10+01:00question_answering AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Gardiner">Mary Gardiner</a> </span>(<em>2004</em>)Tue Jan 29 08:07:10 CET 2008ZZZ-TREC13AnswerFinder at {TREC} 20042004question_answering AnswerFinder molla_publication http://www.bibsonomy.org/bibtex/28d953ca54eb2d90819cd88d9c01d54f9/diego_madiego_ma2008-01-29T07:32:31+01:00AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/van Zaanen">Menno van Zaanen</a> </span>(<em>2005</em>)Tue Jan 29 07:32:31 CET 2008ZZZ-ALTW05Learning of Graph Rules for Question Answering2005AnswerFinder molla_publication http://www.bibsonomy.org/bibtex/2f6eb57c10e7b0ed026b6d3169c2abdfe/diego_madiego_ma2008-01-29T07:24:12+01:00AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/van Zaanen">Menno van Zaanen</a>, <a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Pizzato">Luiz Pizzato</a> </span><em>Proceedings TREC 2006, </em><em>page 8 pages. </em>(<em>2007</em>)Tue Jan 29 07:24:12 CET 2008Proceedings TREC 20068 pagesAnswerFinder at TREC 20062007AnswerFinder molla_publication This article describes the AnswerFinder question answering system and its participation in the TREC 2006 question answering competition. This year there have been several improvements in the AnswerFinder system, although most of them in the implementation sphere. The actual functionality used this year is almost exactly the same as last year, but many bugs are fixed and the efficiency of the system has improved much. This allows for more extensive parameter tuning. Here we will also present an error analysis of the current AnswerFinder system.http://www.bibsonomy.org/bibtex/23eb2ff36ad09d69729f2e7583357824f/diego_madiego_ma2008-01-29T07:22:02+01:00AnswerFinder inf_retrieval molla_publication <span class="authorEditorList"><a href="/author/Pizzato">Luiz Pizzato</a>, and <a href="/author/Mollá">Diego Mollá</a> </span><em>Proceedings ALTW, </em><em> 5, </em><em>page 92-99. </em>(<em>2007</em>)Tue Jan 29 07:22:02 CET 2008Proceedings ALTW92-99Question Prediction Language Model52007AnswerFinder inf_retrieval molla_publication This paper proposes the use of a language representation that specifies the relationship between terms of a sentence using question words. The proposed representation is tailored to help the search for documents containing an answer for a natural language question. This study presents the construction of this language model, the framework where it is used, and its evaluation.http://www.bibsonomy.org/bibtex/2202b97875a0ca06dba67da3f7febfc86/diego_madiego_ma2008-01-29T07:21:37+01:00AnswerFinder named_entities speech molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, <a href="/author/van Zaanen">Menno van Zaanen</a>, and <a href="/author/Cassidy">Steve Cassidy</a> </span><em>Proc. ALTW 2007, </em><em> 5, </em><em>page 57-65. </em>(<em>2007</em>)Tue Jan 29 07:21:37 CET 2008Proc. ALTW 200757-65Named Entity Recognition in Question Answering of Speech Data52007AnswerFinder named_entities speech molla_publication Question answering on speech transcripts (QAst) is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity (NE) recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second (out of three participants) in one of the QAst subtasks.http://www.bibsonomy.org/bibtex/289ee81638dd47b1b73db44a450fcc9c6/diego_madiego_ma2008-01-29T07:21:22+01:00AnswerFinder graphs molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/van Zaanen">Menno van Zaanen</a> </span>(<em>2006</em>)Tue Jan 29 07:21:22 CET 2008ZZZ-TREC14AnswerFinder at {TREC} 20052006AnswerFinder graphs molla_publication AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast development of question-answering systems for their deployment in the TREC tasks and other applications. The AnswerFinder modules use XML to express the services they provide, and they can be queried with XML for their services. The QA method now incorporates graph-based methods to compute the answerhood of a sentence and pin-point the answer. The system uses a set of graph-based rules that are learnt automatically. Unfortunately the system could not be completed and debugged before the TREC deadline and the runs did not fare well. Currently we are debugging and evaluating the system.http://www.bibsonomy.org/bibtex/26fbb4cafafc5651d244edd8fd16e435c/diego_madiego_ma2008-01-29T07:13:18+01:00AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a> </span><em>Proc. ALTW03, </em><em>page 130-137. </em><em>Melbourne, </em>(<em>2003</em>)Tue Jan 29 07:13:18 CET 2008MelbourneProc. ALTW03130-137Towards Semantic-Based Overlap Measures for Question Answering2003AnswerFinder molla_publication http://www.bibsonomy.org/bibtex/2fcafbf38f1cb4c5225ea22e699e426aa/diego_madiego_ma2008-01-29T07:13:17+01:00AnswerFinder molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a> </span><em>Proc. TREC 2003, </em>(<em>2003</em>)Tue Jan 29 07:13:17 CET 2008Proc. TREC 2003AnswerFinder in {TREC} 20032003AnswerFinder molla_publication