BibSonomyburst/user/diego_ma/answer_extractionBibSonomy RSS feed for /user/diego_ma/answer_extraction2012-02-17T00:29:10+01:00http://www.bibsonomy.org/bibtex/2449b4548c23384e9a02234898bdc9715/diego_madiego_ma2008-01-29T09:03:47+01:00answer_extraction evaluation molla_publication <span class="authorEditorList"><a href="/author/Schwitter">Rolf Schwitter</a>, <a href="/author/Mollá">Diego Mollá</a>, <a href="/author/Fournier">Rachel Fournier</a>, and <a href="/author/Hess">Michael Hess</a> </span><em>page 20-27. </em>(<em>2000</em>)Tue Jan 29 09:03:47 CET 2008ZZZ-Brill:200020-27Answer Extraction -- Towards Better Evaluations of {NLP} Systems2000answer_extraction evaluation molla_publication We argue that reading comprehension tests are not particularly suited for the evaluation of NLP systems. Reading comprehension tests are specifically designed to evaluate human reading skills, and these require vast amounts of world knowledge and common-sense reasoning capabilities. Experience has shown that this kind of full-fledged question answering (QA) over texts from a wide range of domains is so difficult for machines as to be far beyond the present state of the art of NLP. To advance the field we propose a much more modest evaluation set-up, viz. Answer Extraction (AE) over texts from highly restricted domains. AE aims at retrieving those sentences from documents that contain the explicit answer to a user query. AE is less ambitious than full-fledged QA but has a number of important advantages over QA. It relies mainly on linguistic knowledge and needs only a very limited amount of world knowledge and few inference rules. However, it requires the solution of a number of key linguistic problems. This makes AE a suitable task to advance NLP techniques in a measurable way. Finally, there is a real demand for working AE systems in technical domains. We outline how evaluation procedures for AE systems over real world domains might look like and discuss their feasibility.http://www.bibsonomy.org/bibtex/297e9a688c93398aaedca1cc8430e5604/diego_madiego_ma2008-01-29T09:03:11+01:00answer_extraction semantics ExtrAns molla_publication <span class="authorEditorList"><a href="/author/Schneider">Gerold Schneider</a>, <a href="/author/Mollá">Diego Mollá</a>, and <a href="/author/Hess">Michael Hess</a> </span><em>Proc. 34. Linguistisches Kolloquium, </em><em>Germersheim, Germany, </em>(<em>1999</em>)Tue Jan 29 09:03:11 CET 2008Germersheim, GermanyProc. 34. Linguistisches {K}olloquiumInkrementelle Minimale Logische {F}ormen f{\"u}r die {A}ntwortextraktion1999answer_extraction semantics ExtrAns molla_publication http://www.bibsonomy.org/bibtex/28c68dc2b9b93d0fb3dc28858c35a0a42/diego_madiego_ma2008-01-29T08:57:50+01:00ExtrAns answer_extraction molla_publication <span class="authorEditorList"><a href="/author/Mollá">Diego Mollá</a>, <a href="/author/Schwitter">Rolf Schwitter</a>, <a href="/author/Hess">Michael Hess</a>, and <a href="/author/Fournier">Rachel Fournier</a> </span><em>Traitement Automatique des Langues</em> <em>41(2):495-522</em> (<em>2000</em>)Tue Jan 29 08:57:50 CET 2008Traitement Automatique des Langues2495-522Extrans, an Answer Extraction System412000ExtrAns answer_extraction molla_publication http://www.bibsonomy.org/bibtex/24fb0f326a00848adbad66d4c583c203b/diego_madiego_ma2007-12-14T02:49:13+01:00evaluation answer_extraction question_answering <span class="authorEditorList"><a href="/author/Brill">Eric Brill</a>, <a href="/author/Charniak">Eugene Charniak</a>, <a href="/author/Harper">Mary Harper</a>, <a href="/author/Light">Marc Light</a>, <a href="/author/Riloff">Ellen Riloff</a>, and <a href="/author/Voorhees">Ellen Voorhees</a> (Eds.). </span><em>Seattle, WA, </em><em>ACL, </em>(<em>2000</em>)Fri Dec 14 02:49:13 CET 2007Seattle, WAProc. {ANLP/NAACL} 2000 Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding SystemsProc. {ANLP/NAACL} 2000 Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding Systems2000evaluation answer_extraction question_answering http://www.bibsonomy.org/bibtex/2a4b43bb88a05f61472a4ea0a66977d77/diego_madiego_ma2007-12-14T02:48:38+01:00answer_extraction ontology <span class="authorEditorList"><a href="/author/Zajac">Rémi Zajac</a> </span><em>Proc. ACL2001, Workshop on Open Domanin QA, </em><em>Toulouse, </em>(<em>2001</em>)Fri Dec 14 02:48:38 CET 2007ToulouseProc. ACL2001, Workshop on Open Domanin QATowards Ontological Question Answering2001answer_extraction ontology This paper presents and ontology-based semantic framework to question answering. Both questions and source text are parsed into underspecified semantic expressions where names of semantic atoms and predicates are defined in an interlingual ontology. Answer retrieval is done using subsumption and unification, and queries are expanded incrementally using ontological rules. Ranking of answers is achieved by using graded unification.http://www.bibsonomy.org/bibtex/2e0755d8af4024080bbe89f346c997b42/diego_madiego_ma2007-12-14T02:47:50+01:00inf_retrieval answer_extraction <span class="authorEditorList"><a href="/author/Voorhees">Ellen M. Voorhees</a> </span><em>Natural Language Engineering</em> <em>7(4):361-378</em> (<em>2001</em>)Fri Dec 14 02:47:50 CET 2007Natural Language Engineering4361-378The {TREC} Question Answering Track72001inf_retrieval answer_extraction http://www.bibsonomy.org/bibtex/26fe5b94948819e09070e3577366f3095/diego_madiego_ma2007-12-14T02:47:49+01:00inf_retrieval answer_extraction <span class="authorEditorList"><a href="/author/Voorhees">Ellen M. Voorhees</a> </span>(<em>2002</em>)<em>Draft . </em>Fri Dec 14 02:47:49 CET 2007DraftOverview of the {TREC} 2001 Question Answering Track2002inf_retrieval answer_extraction http://www.bibsonomy.org/bibtex/218533b8cc3f2a7c501a3c2462939e216/diego_madiego_ma2007-12-14T02:45:25+01:00answer_extraction <span class="authorEditorList"><a href="/author/Purver">Matthew Purver</a> </span><em>University of Cambridge, </em>(<em>October 2000</em>)Fri Dec 14 02:45:25 CET 2007OctoberSimplistic Question Answering2000answer_extraction The aim of this project was to develop a system that could identify text passages which answer a question. The approach taken used ideas from various participants in the recent TREC-8 conference, and added the use of notions on sentence structure --- particularly structural information and matching. The system was successfully tested on training data incorporating a wide range of sentence structure phenomena. Performance was evaluated in blind tests on two sets of data and results were encouraging, with good levels of both recall and precision being achieved.http://www.bibsonomy.org/bibtex/24a3ed337ae5b8a373287532a4a5b1182/diego_madiego_ma2007-12-14T02:45:17+01:00answer_extraction ambiguity logic <span class="authorEditorList"><a href="/author/Pratt-Hartmann">Ian Pratt-Hartmann</a> </span>(<em>August 1999</em>)<em>Draft for internal use only . </em>Fri Dec 14 02:45:17 CET 2007AugustDraft for internal use onlyInference Problems in {ExtrAns}: Quick Summary1999answer_extraction ambiguity logic http://www.bibsonomy.org/bibtex/288be4568d6b0b016f2cdcfe8e4a4e4db/diego_madiego_ma2007-12-14T02:44:37+01:00answer_extraction <span class="authorEditorList"><a href="/author/O&#039;Connor">John O&#039;Connor</a> </span><em>Information Processing \&amp; Management</em> <em>11(5/7):155-164</em> (<em>1975</em>)Fri Dec 14 02:44:37 CET 2007Information Processing \& Management5/7155-164Retrieval of Answer Sentences and Answer-Figures from Papers by Text Searching111975answer_extraction http://www.bibsonomy.org/bibtex/2100911b3cfa200051c9b6bed128b5672/diego_madiego_ma2007-12-14T02:42:51+01:00answer_extraction <span class="authorEditorList"><a href="/author/Mann">Gideon S. Mann</a> </span><em>Proc. Workshop on Open-Domain Question Answering at ACL 2001, </em><em>Toulouse, France, </em>(<em>2001</em>)Fri Dec 14 02:42:51 CET 2007Toulouse, FranceProc. Workshop on Open-Domain Question Answering at ACL 2001A Statistical Method for Short Answer Extraction2001answer_extraction This paper presents a simple, general method for using the Mutual Information (MI) statistic trained on unannotated trivia questions to estimate question class/ semantic tag correlation...http://www.bibsonomy.org/bibtex/2c0fe448171f04d2db2f304bd8146ffab/diego_madiego_ma2007-12-14T02:40:24+01:00answer_extraction <span class="authorEditorList"><a href="/author/Hirschman">Lynette Hirschman</a>, <a href="/author/Light">Marc Light</a>, <a href="/author/Breck">Eric Breck</a>, and <a href="/author/Burger">John D. Burger</a> </span><em>Proc. ACL&#039;99, </em><em>University of Maryland, </em>(<em>1999</em>)Fri Dec 14 02:40:24 CET 2007Proc. ACL'99Deep {R}ead: A Reading Comprehension System1999answer_extraction This paper describes initial work on {\bf Deep Read}, and automated reading comprehension system that accepts arbitrary text input (a story) and answers questions about it. We have adquired a corpus of 60 development and 60 test stories of $3^{rd}$ to $6^{th}$ grade material; each story is followed by short-answer questions (an answer key was also provided). We used these to construct and evaluate a baseline system that uses pattern matching (bag-of-words) techniques augmented with additional automated linguistic processing (stemming, name identification, semantic class identification, and pronoun resolution). This simple system retrieves the sentence containing the answer 30-40\% of the time.http://www.bibsonomy.org/bibtex/2744c289f1b9739185b7425f969fd6a56/diego_madiego_ma2007-12-14T02:40:01+01:00answer_extraction <span class="authorEditorList"><a href="/author/Harabagiu">Sanda M. Harabagiu</a>, <a href="/author/Pasca">Marius A. Pasca</a>, and <a href="/author/Maiorano">Steven I. Maiorano</a> </span><em>Proc. COLING-2000, </em>(<em>2000</em>)Fri Dec 14 02:40:01 CET 2007Proc. COLING-2000Experiments with Open-Domain Textual Question Answering2000answer_extraction This paper describes the integration of several knowledge-based natural language processing techniques into a Question Answering system, capable of mining textual answers from large collections of texts. Surprizing quality is achieved when several lightweight knowledge-based NLP techniques complement mostly shallow, surface-based approaches.http://www.bibsonomy.org/bibtex/2380b4b132d8f3219a5a9c6a471dadc14/diego_madiego_ma2007-12-14T02:38:27+01:00answer_extraction <span class="authorEditorList"><a href="/author/Echihabi">Abdessamad Echihabi</a>, <a href="/author/Hermjakob">Ulf Hermjakob</a>, <a href="/author/Hovy">Eduard Hovy</a>, <a href="/author/Marcu">Daniel Marcu</a>, <a href="/author/Melz">Eric Melz</a>, and <a href="/author/Ravichandran">Deepak Ravichandran</a> </span><em>Advances in Textual Question Answering, </em><em>Kluwer, </em>(<em>2004</em>)Fri Dec 14 02:38:27 CET 2007Advances in Textual Question AnsweringHow to Select an Answer String?2004answer_extraction Given a question Q and a sentence/paragraph SP that is likely to contain the answer to Q, an answer selection module is supposed to select the ``exact'' answer sub-string A $\subset$ SP. We study three distinct approaches to solving this problem: one approach uses algorithms that rely on rich knowledge bases and sophisticated syntactic/semantic processing; one approach uses patterns that are learned in an unsupervised manner from the web, using computational biology-inspired alignment algorithms; and one approach uses statistical noisy-channel algorithms similar to those used in machine translation. We assess the strengths and weaknesses of these three approaches and show how they can be combined using a maximum entropy-based framework.http://www.bibsonomy.org/bibtex/27df818c34f3b722faade6124807a547f/diego_madiego_ma2007-12-14T02:36:30+01:00question_answering answer_extraction <span class="authorEditorList"><a href="/author/Breck">Eric Breck</a>, <a href="/author/Burger">John Burger</a>, <a href="/author/House">David House</a>, <a href="/author/Light">Marc Light</a>, and <a href="/author/Mani">Inderjeet Mani</a> </span><em>Proc. 1999 AAAI Fall Symposium on Question Answering Systems, </em>(<em>1999</em>)<em>Forthcoming . </em>Fri Dec 14 02:36:30 CET 2007Proc. 1999 {AAAI} Fall Symposium on Question Answering SystemsForthcomingQuestion Answering from Large Document Collections1999question_answering answer_extraction http://www.bibsonomy.org/bibtex/25536727cce39c9bf5a8cc219f47d5f5d/diego_madiego_ma2007-12-14T02:36:29+01:00answer_extraction question_answering <span class="authorEditorList"><a href="/author/Breck">Eric Breck</a>, <a href="/author/Burger">John Burger</a>, <a href="/author/Ferro">Lisa Ferro</a>, <a href="/author/House">David House</a>, <a href="/author/Light">Marc Light</a>, and <a href="/author/Mani">Inderjeet Mani</a> </span>(<em>1999</em>)Fri Dec 14 02:36:29 CET 2007A Sys Called {Qanda}1999answer_extraction question_answering