Notes:
The passage retrieval module is a component of a dialog system that is responsible for retrieving relevant information from a knowledge base or corpus of text. This module typically receives input from a variety of other modules, such as the natural language understanding module, the conversation control module, and the ontology extraction module. It then uses this information to search a knowledge base or corpus of text for passages that are relevant to the current conversation.
The passage retrieval module typically includes a set of rules or algorithms that define how the system should search for and retrieve relevant information. For example, the module may use rules to identify the key words and phrases in the user’s input, and then use these words and phrases to search for relevant passages in the knowledge base or corpus. It may also use algorithms to rank the retrieved passages based on their relevance or likelihood, and then select the most appropriate ones for inclusion in the system’s response.
Once the relevant passages have been retrieved, they are passed to the language generation module, which converts them into natural language text that can be output to the user. The language generation module may also apply additional processing, such as summarization or paraphrasing, to make the generated text more concise and coherent.
Overall, the function of the passage retrieval module is to help the dialog system retrieve relevant information from a knowledge base or corpus of text. This can help improve the quality and accuracy of the system’s responses, and make the interaction more effective and informative for the user.
See also:
Research of passage retrieval for question answering system [PDF] from 144.214.124.123X Li – 2010 – 144.214.124.123 … has long been studied in IR and recently has been an important component in QA systems. The passage retrieval module is usually added as an intermediate stage between the document retrieval module and answer extraction module. It can facilitate … Related articles – Library Search – All 2 versions
Elhuyar-IXA: semantic relatedness and cross-lingual passage retrieval [PDF] from elhuyar.orgE Agirre, O Ansa, X Arregi, M de Lacalle… – … Access Evaluation I. …, 2011 – Springer … s,sdis max =t’t, w ? (5) ( ) { } 0 where ‘ 1 ‘, MWU Z Z ss, ss smw (6) 2.3 Passage Retrieval The purpose of the passage retrieval module is to retrieve passages from the document collection which are likely to contain an answer. … Cited by 2 – Related articles – All 8 versions
N-gram vs. keyword-based passage retrieval for question answering [PDF] from psu.eduD Buscaldi, J Gomez, P Rosso… – Evaluation of Multilingual …, 2007 – Springer … At the same time, the question is passed to the Passage Retrieval module, which generates the passages used by the Answer Extraction (AE) module together with the information collected in the question analysis phase in order to extract the final answer. … Cited by 11 – Related articles – BL Direct – All 9 versions
On interface compatibility and mediation of Web services B Lin – 2010 – 144.214.124.123 … The passage retrieval module is usually added as an intermediate stage between the document retrieval module and answer extraction module. It can facilitate quick answer extraction and improve the efficiency of answer finding by users. … Cached – All 2 versions
An answer passage retrieval strategy for web-based question answering X Li, D Hu, T Hao, E Chen… – Proceedings of the 2nd …, 2007 – dl.acm.org … 2. OVERVIEW OF OUR SYSTEM Our web-based QA system has four components: question analysis module, document retrieval module, passage retrieval module, and answer extraction module, as shown in Figure 1. The system firstly makes an analysis of a question. … Cited by 2 – Related articles – All 2 versions
What is not in the bag of words for why-qa? [PDF] from aclweb.orgS Verberne, L Boves, N Oostdijk… – Computational Linguistics, 2010 – MIT Press … 2005). Therefore, it is interesting to investigate which questions are answered in the top 150 and not in the top 10 by our passage retrieval module. … The input data for our re-ranking experiments is the output of the passage retrieval module. … Cited by 5 – Related articles – All 25 versions
[PDF] UCD IIRG at TAC 2010 KBP Slot Filling Task [PDF] from nist.govL Byrne… – Third Text Analysis Conference (TAC 2010), 2010 – nist.gov … Page 2. question is asking about, eg a person, a date, a location, etc. A query is also constructed from selected question terms and is given to the Passage Retrieval module, which identifies passages of text that are likely to contain an answer. … Cited by 5 – Related articles – View as HTML
Multilingual question answering through intermediate translation: Lcc’s poweranswer at qa@ clef 2007 [PDF] from rug.nlM Bowden, M Olteanu, P Suriyentrakorn… – … in Multilingual and …, 2008 – Springer … Question Logic Transformation COGEX World Kowledge Axioms Processing Question Module Question Module Passage Retrieval Module Answer Processing Transformation Answer Logic Syntactic Parsing Named Entity Recognition Documents Answer … Cited by 5 – Related articles – All 26 versions
Biological question answering with syntactic and semantic feature matching and an improved mean reciprocal ranking measurement [PDF] from sinica.edu.twRTK Lin, J Liang-Te Chiu, HJ Dai… – … , 2008. IRI 2008. …, 2008 – ieeexplore.ieee.org … IEEE 184 Page 2. word list. The remaining phrase segments are sent to the passage retrieval module as keywords for a Google search. Query modification is used to improve recall for queries where Google returns pages. First … Cited by 3 – Related articles – All 5 versions
Effects of answer weight boosting in strategy-driven question answering [PDF] from kaist.ac.krHJ Oh, SH Myaeng… – Information Processing & Management, 2011 – Elsevier Related articles – All 4 versions
Spoken QA based on a passage retrieval engine [PDF] from pitt.eduE Sanchis, D Buscaldi, S Grau… – Spoken Language …, 2006 – ieeexplore.ieee.org … tion (AE). The passage retrieval module is based on finding the passages more similar to the question . To do that, a distance measure based on the n-gram similitude between the question and the passage is defined. This … Cited by 9 – Related articles – All 2 versions
Robust question answering for speech transcripts: UPC experience in QAst 2008 [PDF] from clef-campaign.orgP Comas… – Evaluating Systems for Multilingual and Multimodal …, 2009 – Springer … Then, these candidates are ranked using a scoring function based on a set of heuristics that measure keyword distance and density[5]. These heuristic measures use approximated matching for AE in automatic transcripts as shown in the passage retrieval module from the … Cited by 7 – Related articles – All 14 versions
Question answering for Portuguese: how much is needed? R Wilkens, A Villavicencio – Advances in Artificial Intelligence-SBIA 2010, 2011 – Springer … Portuguese. The documents retrieved by the tool are ranked in order of relevance and passed to the passage retrieval module. … PALAVRAS). The passage retrieval module takes the document retrieved by the IR module and splits it into sentences. … Related articles – All 3 versions
Language Technologies: Question Answering in Speech Transcripts J Turmo, M Surdeanu, O Galibert… – Computers in the Human …, 2009 – Springer … This information is used to build an index consisting of two parts. The first part, built on the lemmatized text, is built using the word lemmas and the recognized named entities. This text is indexed and used by the passage retrieval module to find relevant passages. … Cited by 1 – Related articles – All 2 versions
[PDF] DefArabicQA: Arabic Definition Question Answering System [PDF] from lrec-conf.orgO Trigui, HL Belguith… – Workshop on Language Resources …, 2010 – lrec-conf.org … Organization | > < What+ be+< topic>? Table 1. Question patterns and their expected answer types used by DefArabicQA system 3.2 Passage retrieval The passage retrieval module collects the top-n snippets retrieved by the Web search engine. … Cited by 2 – Related articles – View as HTML – All 3 versions
Ihardetsi: a Basque question answering system at QA@ CLEF 2008 [PDF] from clef-campaign.orgO Ansa, X Arregi, A Otegi… – Evaluating Systems for …, 2009 – Springer … Concretely, search terms are extracted for the passage retrieval module, and both the question type (factoid, list or definition) and the expected answer type along with some lexical information are passed to the answer extraction module. … Cited by 5 – Related articles – All 6 versions
Ihardetsi: A Question Answering system for Basque built on reused linguistic processors I Alegria, O Ansa, X Arregi, A Otegi… – Proc. SALTMIL 2009 …, 2009 – isca-speech.org … These descriptors constitute the documentation support of the system. As it is common in the question answering systems Ihardetsi is founded on three main modules: the question analysis module, the passage retrieval module and the answer extraction module. … Cited by 1 – Related articles – All 3 versions
A supervised learning approach to biological question answering [PDF] from ntu.edu.twRTK Lin, JLT Chiu, HJ Dai, RTH Tsai… – Integrated Computer- …, 2009 – IOS Press … improve recall. 3.1.2. Passage retrieval The passage retrieval module is a Google-interfacing program that sends queries to Google and retrieves a collection of web pages, which are sent to the answer extraction module. In the … Cited by 4 – Related articles – All 7 versions
A survey of text mining techniques and applications [PDF] from academypublisher.comV Gupta… – Journal of Emerging Technologies in …, 2009 – academypublisher.com … 2009 ACADEMY PUBLISHER Page 8. Figure 15. QUASAR QUESTION ANSWERING SYSTEM In Passage Retrieval module, user question is handed over also to the JIRS Passage Retrieval system, more specifically to its Search Engine and N-grams Extraction components. … Cited by 20 – Related articles – All 14 versions
An Arabic Question-Answering system for factoid questions W Brini, M Ellouze, S Mesfar… – … Engineering, 2009. NLP …, 2009 – ieeexplore.ieee.org … The proposed system is composed of three modules: A question analysis module, a passage retrieval module and an answer extraction module. To process these three modules we use the NooJ Platform which represents a linguistic development environment. … Cited by 3 – Related articles – All 2 versions
[PDF] Construction of Text Summarization Corpus for the credibility of Information on the Web [PDF] from ffzg.hrM Nakano, H Shibuki, R Miyazaki… – Proceedings of the 7th …, 2010 – hnk.ffzg.hr … Figure 2 shows the outline of the system we attempt to develop in order to generate survey reports. An inputted query statement is passed to the passage retrieval module and the timeline analysis module. In the passage retrieval … Cited by 1 – Related articles – View as HTML – All 2 versions
System and method for providing answers to questions EW Brown, D Ferrucci, A Lally… – US Patent App. 12/ …, 2008 – Google Patents Page 1. US 20090287678A1 (i9) United States (12) Patent Application Publication oo) Pub. No.: US 2009/0287678 Al Brown et al. (43) Pub. Date: Nov. 19,2009 (54) SYSTEM AND METHOD FOR PROVIDING ANSWERS TO … Cited by 1 – Related articles – All 2 versions
[PDF] Combining multiple resources, evidence and criteria for genomic information retrieval [PDF] from cmu.eduL Si, J Lu… – The Fifteenth Text REtrieval Conference …, 2006 – www-cgi.cs.cmu.edu … Our aspect retrieval module considers both topical relevance and the coverage of aspects. Topical relevance can be directly measured by the scores from the passage retrieval module (with or without rescoring in the post-processing module). … Cited by 3 – Related articles – View as HTML – All 15 versions
[PDF] Implementation of the ArabiQA Question Answering System’s components [PDF] from psu.eduY Benajiba, P Rosso… – Proc. Workshop on Arabic Natural …, 2007 – Citeseer … In the second section we describe the generic architecture of the system. We make a special focus on named entity recognition in Arabic in section Three. The implementation of the passage retrieval module is presented in section Four. … Cited by 11 – Related articles – View as HTML – All 5 versions
[PDF] Two approaches for multilingual question answering: Merging passages vs. merging answers [PDF] from 140.109.19.106RM Aceves-Pérez, M Montes-y-Gómez… – International Journal …, 2008 – 140.109.19.106 … of the pipeline architecture of monolingual QA systems (which includes three main modules, one for question classification, one for passage retrieval, and one for answer extraction) to achieve this combination at two different stages: after the passage retrieval module by mixing … Cited by 4 – Related articles – View as HTML – All 13 versions
LCC’s poweranswer at QA@ CLEF 2006 [PDF] from clef-campaign.orgM Bowden, M Olteanu, P Suriyentrakor… – … of Multilingual and …, 2007 – Springer … Question Logic Transformation COGEX World Kowledge Axioms Processing Question Module Question Module Passage Retrieval Module Answer Processing Transformation Answer Logic Syntactic Parsing Named Entity Recognition Documents Answer … Cited by 12 – Related articles – BL Direct – All 9 versions
Idsay: Question answering for portuguese [PDF] from clef-campaign.orgG Carvalho, D de Matos… – Evaluating Systems for Multilingual …, 2009 – Springer … both. This list of documents is then processed by the passage retrieval module, responsible for the search of passages from the documents that contain the search string, and with length (number of words) up to a given limit (60). … Cited by 3 – Related articles – All 9 versions
Methods for using textual entailment in open-domain question answering [PDF] from upenn.eduS Harabagiu… – … of the 21st International Conference on …, 2006 – dl.acm.org … 1http://www.pascal-network.org/Challenges/RTE 905 Page 2. Processing Question Module (QP) Passage Retrieval Module (PR) Answer Type Expected Keywords Module Answer Processing (AP) Ranked List of Answers TEXTUAL ENTAILMENT … Cited by 87 – Related articles – BL Direct – All 22 versions
[PDF] Chinese Character Expansion for Retrieving Japanese Paraphrases [PDF] from psu.eduT Takenobu, T Yoshiki… – 2008 – Citeseer … The system consists of the following three modules: 1. A passage retrieval module which retrieves paraphrase candidates from a collection of passages. 2. A filtering module which filters out irrelevant retrieved candidates based on syntactic and seman- tic appropriateness. … Related articles – View as HTML – All 7 versions
METHOD FOR PROCESSING NATURAL LANGUAGE QUESTIONS AND APPARATUS THEREOF DA Ferrucci, MA Li, Y Pan, ZM Qiu… – US Patent App. 12/ …, 2010 – Google Patents … [0007] FIG. 1 illustrates a general architecture of existing QA systems. As shown in FIG. 1, a general QA system includes a question processing module 101, a document/ passage retrieval module 103, and an answer processing mod- ule 105. … All 2 versions
The impact of frame semantic annotation levels, frame-alignment techniques, and fusion methods on factoid answer processing B Ofoghi, J Yearwood… – Journal of the American Society …, 2009 – Wiley Online Library … Data. The subset of TREC 2004 factoid questions for which the passage- retrieval module can retrieve correct answers in the top 10 passages will be regarded as the first test set. This subset includes 143 questions (out of 230 factoid questions in TREC 2004; Voorhees, 2004). … Cited by 1 – Related articles – All 7 versions
[BOOK] Computational Processing of the Portuguese Language: 9th International Conference, PROPOR 2010, Porto Alegre, RS, Brazil, April 27-30, 2010. … TAS Pardo – 2010 – books.google.com … separator and dec- imal separator. The passage retrieval module was improved in a way that they become closer to meaningful sentences, and list questions were considered for the ?rst time. Some minor adjustments were … Related articles – Library Search – All 5 versions
BESearch: A Supervised Learning Approach to Search for Molecular Event Participants [PDF] from tku.edu.twRTH Tsai, HJ Dai, HC Hung… – … , 2007. IRI 2007. …, 2007 – ieeexplore.ieee.org … In this section, we describe the five main components of our form-based biomedical entity search engine, namely, the search interface, the query construction module, the passage retrieval module, the candidate extraction and feature generation module, and the ranking … Cited by 3 – Related articles – All 9 versions
Improving IdSay: A Characterization of Strengths and Weaknesses in Question Answering Systems for Portuguese G Carvalho, D de Matos… – Computational Processing of the …, 2010 – Springer … separator and dec- imal separator. The passage retrieval module was improved in a way that they become closer to meaningful sentences, and list questions were considered for the first time. Some minor adjustments were … Related articles – All 2 versions
[PDF] Lymba’s PowerAnswer 4 in TREC 2007 [PDF] from nist.govD Moldovan, C Clark… – Proceedings of the Sixteenth Text …, 2007 – trec.nist.gov … Page 2. Question Logic Transformation COGEX World Kowledge Axioms Processing Question Module Question Module Passage Retrieval Module Answer Processing Transformation Answer Logic Syntactic Parsing Named Entity Recognition Documents Answer … Cited by 15 – Related articles – View as HTML – All 4 versions
Automatic question answering from Web documents X Li, D Hu, H Li, T Hao, E Chen… – Wuhan University Journal of …, 2007 – Springer … It should be more efficient if QA systems reduce the size of document to be processed. For this purpose, the passage retrieval module is added as an intermediate stage between the document retrieval module and answer extraction module. … Cited by 2 – Related articles – BL Direct
Quasar: The question answering system of the universidad politécnica de valencia [PDF] from upv.esJ Gómez-Soriano, D Buscaldi, E Asensi… – Accessing Multilingual …, 2006 – Springer … In the cross-language task, the Passage Retrieval module worked well despite the generally acknowledged low Page 10. 448 JM Gómez-Soriano et al. quality of web translations, allowing to obtain results slightly worse than those obtained in the monolingual task. … Cited by 17 – Related articles – BL Direct – All 5 versions
Improving passage retrieval using interactive elicition and statistical modeling [PDF] from dtic.milD He – 2006 – DTIC Document … However, a subsequent inter- annotator consistency study conducted at the Uni- versity of Maryland showed that our HARD-20003 passage retrieval module was far below human per- formance on the same task. … 2.1 The 2003 Passage Retrieval Module … Cited by 4 – Related articles – All 24 versions
Boosting Chinese question answering with two lightweight methods: ABSPs and SCO-QAT [PDF] from sinica.edu.twCW Lee, MY Day, CL Sung, YH Lee… – ACM Transactions on …, 2008 – dl.acm.org Page 1. 12 Boosting Chinese Question Answering with Two Lightweight Methods: ABSPs and SCO-QAT CHENG-WEI LEE National Tsing-Hua University Taiwan and Academia Sinica and MIN-YUH DAY, CHENG-LUNG SUNG … Cited by 2 – Related articles – All 11 versions
QUESTION ANSWERING USING QUESTION CLASSIFICATION AND DOCUMENT TAGGING Y Chali – Applied Artificial Intelligence, 2009 – Taylor & Francis Related articles – All 5 versions
A comparison of genetic algorithms for optimizing linguistically informed IR in question answering [PDF] from uu.seJ Tiedemann – AI* IA 2007: Artificial Intelligence and Human-Oriented …, 2007 – Springer … formed natural language question. The consequence of this is that the passage retrieval module in a QA system has to maximize the use of all linguistic clues in the given question not only the lexical ones. In our approach we … Cited by 8 – Related articles – BL Direct – All 13 versions
[PDF] The upv at qa@ clef 2006 [PDF] from clef-campaign.orgD Buscaldi, JM Gómez, P Rosso… – Working Notes for the …, 2006 – clef-campaign.org … At the same time, the question is passed to the Passage Retrieval module, which generates the passages used by the Answer Extraction (AE) module together with the information collected in the question analysis phase in order to extract the final answer. … Cited by 10 – Related articles – View as HTML – All 11 versions
[PDF] A temporally-enhanced PowerAnswer in TREC 2006 [PDF] from unipi.itD Moldovan, M Bowden… – Text Retrieval Conference ( …, 2006 – mailserver.di.unipi.it … Question Logic Transformation COGEX World Kowledge Axioms Processing Question Module Module Passage Retrieval Module Answer Processing Transformation Answer Logic Syntactic Parsing Named Entity Recognition Documents Answer Reference Resolution QLF ALF … Cited by 29 – Related articles – View as HTML – All 4 versions
Experiments in speech driven question answering [PDF] from uva.esC González-Ferreras… – … Workshop, 2008. SLT …, 2008 – ieeexplore.ieee.org … 3.2.3. Answer extraction The input of this module is constituted by the passages returned by the passage retrieval module and the constraints (including the expected type of the answer) obtained through the question analysis module. … Cited by 1 – Related articles – All 2 versions
SYSTEM AND METHOD FOR PROVIDING QUESTION AND ANSWERS WITH DEFERRED TYPE EVALUATION J Fan, D Ferrucci, DC Gondek… – US Patent App. 12/ …, 2008 – Google Patents Page 1. US 20090292687A1 (i9) United States (12) Patent Application Publication (i0) Pub. No.: US 2009/0292687 Al Fan et al. (43) Pub. Date: Nov. 26,2009 (54) SYSTEM AND METHOD FOR PROVIDING QUESTION AND … All 2 versions
[PDF] Question answering with LCC’s CHAUCER at TREC 2006 [PDF] from unipi.itS Harabagiu, A Hickl, J Williams, J Bensley… – Proc. …, 2006 – mailserver.di.unipi.it … First, the top 200 documents were retrieved us- ing an expanded keyword query; these documents were then passed to a Passage Retrieval module which was used to extract the most relevant text passages from each document. … Cited by 4 – Related articles – View as HTML – All 2 versions
QUESTIONS AND ANSWERS GENERATION PA Duboue, DA Ferrucci, DC Gondek… – US Patent App. 12/ …, 2010 – Google Patents Page 1. US 20110125734A1 (i9) United States (12) Patent Application Publication oo) Pub. No.: US 2011/0125734 Al Duboue et al. (43) Pub. Date: May 26,2011 (54) QUESTIONS AND ANSWERS GENERATION Publication … All 2 versions
HARD experiment at Maryland: from need negotiation to automated HARD process [PDF] from dtic.milD He – 2006 – DTIC Document … Our passage retrieval module assumes that the relevance of a passage is related to the frequency of the query terms in the passage, the importance of these query terms (ie their weights), and the relevance of the document that contains the passage to the query. … Cited by 18 – Related articles – All 18 versions
[PDF] Mining knowledge from wikipedia for the question answering task [PDF] from brandeis.eduD Buscaldi… – Proceedings of the International …, 2006 – pages.cs.brandeis.edu … candidates, or did not return any at all. Similarly, 5 generic answers were actually present in Wikipedia but the passage retrieval module did not find passages where the answer was present. This means that with a “perfect” passage … Cited by 22 – Related articles – View as HTML – All 7 versions
The TALP-QA system for Spanish at CLEF 2005 [PDF] from psu.eduD Ferrés, S Kanaan, A Ageno, E González… – Accessing Multilingual …, 2006 – Springer … For factoid questions the two runs submitted differ in the parameters of the passage retrieval module: i) the maximum number of documents retrieved was 1200 (run1) and 1000 (run2), ii) the windows proximity was: (run1: 60 to 240 lemmas; run2: 80 to 220 lemmas), iii) the … Cited by 10 – Related articles – BL Direct – All 5 versions
The GeoTALP-IR System at GeoCLEF 2005: Experiments Using a QA-Based IR System, Linguistic Analysis, and a Geographical Thesaurus [PDF] from upc.eduD Ferrés, A Ageno… – Accessing Multilingual Information …, 2006 – Springer … English task. The GIR system is based on Lucene and uses a modified version of the Passage Retrieval module of the TALP Question Answering (QA) system presented at CLEF 2004 and TREC 2004 QA evaluation tasks. We … Cited by 9 – Related articles – BL Direct – All 10 versions
An experiment about using copulative and comparative sentences as constraining relations A Soto, JA Olivas, FP Romero… – … Systems Design and …, 2009 – ieeexplore.ieee.org … order to find relevant passages. Then, the passage retrieval module uses search engines to retrieve the set of passages (ie text paragraphs, sentences) more likely to contain the answer. Subsequently a filter preselects small … Cited by 1 – Related articles – All 3 versions
Mexican Experience in Spanish Question Answering [PDF] from scielo.org.mxM Montes y Gómez, L Villaseñor Pineda… – Computación y …, 2008 – scielo.org.mx Page 1. Mexican Experience in Spanish Question Answering Experiencia Mexicana en la Búsqueda de Respuestas en Español Manuel Montes y Gómez, Luis Villaseñor Pineda and Aurelio López López Laboratorio de Tecnologías … All 17 versions
[PDF] Arabic Question Answering [PDF] from upv.esY Benajiba… – Diploma of advanced studies. Technical …, 2007 – users.dsic.upv.es … 1. Question Analysis module: it determines the type of the given question (in order to inform the Answer Extraction (AE) module about the expected type of answer), the question keywords (used by the passage retrieval module as 11 Page 18. … Cited by 4 – Related articles – View as HTML – All 2 versions
INFERRING LEXICAL ANSWER TYPES OF QUESTIONS FROM CONTEXT JW Murdock IV – US Patent App. 12/570,575, 2009 – Google Patents … expansion (see, eg, http:// en.wikipedia.org/wiki/Query_expansion); a Document Titles (Document Retrieval in Title Sources) module implementing functions for detecting a candidate answer (from sources 11 and 21); an Entities From Passage Retrieval module imple- menting … All 2 versions
[PDF] The LIA-Thales summarization system at DUC-2006 [PDF] from berkeley.eduB Favre, F Béchet, P Bellot, F Boudin… – Proceedings of the …, 2006 – icsi.berkeley.edu … The last two components have been used for DUC 2006: System 4 (S4) presented in this section is based on the Passage Retrieval module of the LIA QA system; System 5 (S5) is based on the Answer Extraction module of the same system. … Cited by 11 – Related articles – View as HTML – All 24 versions
[PDF] Research of Passage Retrieval for Question Answering System [PDF] from cityu.edu.hk??????????????? – 2010 – lbms03.cityu.edu.hk … has long been studied in IR and recently has been an important component in QA systems. The passage retrieval module is usually added as an intermediate stage between the document retrieval module and answer extraction module. It can facilitate … View as HTML
[PDF] A Machine Learning Approach for an Indonesian-English Cross Language Question Answering System [PDF] from tut.ac.jpA Purwarianti, M Tsuchiya… – IEICE transactions on …, 2007 – slp.ics.tut.ac.jp Page 1. IEICE TRANS. INF. & SYST., VOL.E90-D, NO.11 NOVEMBER 2007 1841 PAPER A Machine Learning Approach for an Indonesian-English Cross Language Question Answering System Ayu PURWARIANTI †a) , Masatoshi … Cited by 1 – Related articles – BL Direct – All 11 versions
Personalized Question Answering: A Use Case for Business Analysis [PDF] from nuigalway.ieVT Thai, S O’Riain, B Davis… – 2006 – vmserver14.nuigalway.ie … The Passage Retrieval module performs text processing of documents and analysis of questions on- the-fly to identify passages that are relevant to the input question. … The following paragraphs below describe each component of the Passage Retrieval module. … Cited by 2 – Related articles – All 18 versions
[PDF] Resource Integration for Question Answering and Geographical Information Retrieval [PDF] from upv.esD Buscaldi – 2007 – dsic.upv.es … 5 2.2 The QUASAR Question Answering System . . . . . 6 2.2.1 Question Analysis Module . . . . . 6 2.2.2 The JIRS Passage Retrieval Module . . . . . 8 2.2.3 Answer Extraction . . . . . 9 2.2.4 Cross-Language module . . … Related articles – View as HTML – All 2 versions
[PDF] Towards an Arabic Question Answering system [PDF] from upv.esP Rosso, Y Benajiba… – Proc. 4th Conf. on Scientific …, 2006 – users.dsic.upv.es … The third Section is devoted to the description of the components which we have already implemented: the Named Entity Recognition system used in our QA system and the Passage Retrieval module. In Section four we describe the components not implemented yet. … Cited by 4 – Related articles – View as HTML – All 2 versions
[PDF] ENGLISH MALAYALAM CROSS-LINGUAL OPEN DOMAIN QUESTION ANSWERING SYSTEM [PDF] from cusat.ac.inPL Nikesh – 2008 – dspace.cusat.ac.in … processor to find out the top 10 ranked documents where the answer to the query can be most likely find out. • The top ranked documents are processed by the passage retrieval module to find out top 5 passages. Page 33. Analysis And Design Page | 15 … Related articles – View as HTML – All 2 versions
[PDF] Chinese-Chinese and English-Chinese question answering with ASQA at NTCIR-6 CLQA [PDF] from tku.edu.twCW Lee, MY Day, CL Sung, YH Lee… – Proceedings of NII- …, 2007 – mail.im.tku.edu.tw … Based on the keywords, the Passage Retrieval module retrieves related passages {P1, P2, P3, …, Pm}, where m ? 100. … For each training question, only the top 200 passages returned by the Passage Retrieval module were collected and tagged with NE and POS tags. … Cited by 5 – Related articles – View as HTML – All 10 versions
Using scenario knowledge in automatic question answering [PDF] from upenn.eduS Harabagiu… – Proceedings of the Workshop on Task-Focused …, 2006 – dl.acm.org … Annotators were tasked with evaluating three types of output from our Q/A system: (1) the ranked list of passages retrieved by our system’s Passage Retrieval module, (2) the list of passages identified as being CE by the scenario, and (3) the set of answers marked as being CE … Cited by 2 – Related articles – All 19 versions
Experiments adapting an open-domain question answering system to the geographical domain using scope-based resources [PDF] from upenn.eduD Ferrés… – Proceedings of the Workshop on Multilingual …, 2006 – dl.acm.org … documents are not useful. Furthermore, a highly accurate Passage Retrieval module is required because frequently the answer occurs in a very small set of passages. • RDQAs are frequently task-based. So, the repertory … Cited by 10 – Related articles – All 23 versions
[PDF] An answer bank for temporal inference [PDF] from ffzg.hrS Harabagiu… – Proceedings of LREC, 2006 – hnk.ffzg.hr … The passage retrieval module for our Q/A system is using the keyword classes to express semantic constraints that are expected to be met by the relevant passages. Some of the semantic constraints are using temporal inference. … Cited by 6 – Related articles – View as HTML – All 9 versions
Toponym Disambiguation in Information Retrieval [PDF] from upv.esD Buscaldi – 2010 – riunet.upv.es … 6.1 The SemQUASAR QA System . . . . . 105 6.1.1 Question Analysis Module . . . . . 107 6.1.2 The Passage Retrieval Module . . . . . 108 6.1.3 WordNet-based Indexing . . . . . 110 6.1.4 Answer Extraction . . . … Cited by 3 – Related articles – All 17 versions
Some Advanced Features Of Cc’s Poweranswer D Moldovan, M Pasca… – Advances in Open Domain …, 2006 – Springer … First, there are few available keywords in the question. Consequently the output from the passage retrieval module is large, especially if the question phrase is a common (“What is a star?”) rather than specific term (“What is phlebotomy?”). … Related articles – All 2 versions
[CITATION] Aspects of sentence retrieval [PDF] from umass.eduVG Murdock – 2006 – ProQuest Cited by 27 – Related articles – Library Search – BL Direct – All 12 versions
[PDF] Exploring shallow answer ranking features in cross-lingual and monolingual factoid question answering [PDF] from rug.nlCW Lee, YH Lee… – Computational Linguistics and …, 2008 – acl.eldoc.ub.rug.nl … 2001]. However, unlike Magnini’s approach, which utilizes the Web as a corpus to help answer questions posed on a local corpus, SCO-QAT uses passages retrieved by the passage retrieval module from the local corpus directly and does not use any word-ignoring rules. … Cited by 1 – Related articles – View as HTML – All 17 versions
[PDF] A Survey of Answer Extraction Techniques in Factoid Question Answering [PDF] from cmu.eduM Wang – Computational Linguistics, 2006 – cs.cmu.edu … semantic role labeling. r Document or passage retrieval module: this module takes the keywords produced by the question analysis module, and uses some search engine to perform document or passage retrieval. Two of the … Related articles – View as HTML – All 3 versions
Using language models in question answering [PDF] from uni-saarland.deA Merkel – 2008 – scidok.sulb.uni-saarland.de … from the previous component are split up into text passages. Then, a re-ranking is done to find the best matching snippets. A special case of the passage retrieval module is selecting just one sentence as text passage. The thesis also covers a statistical approach to this part … Related articles – All 6 versions
An XML Framework for a Basque Question Answering System [PDF] from eiieo.orgO Ansa, X Arregi, A Otegi… – Flexible Query Answering …, 2006 – Springer … next tasks. Concretely, a set of search terms are extracted for the passage retrieval module, and the expected answer type along with some lexical and syntactic information is passed to the answer extraction module. The question … Related articles – BL Direct – All 3 versions
Relation based models for passage retrieval in open domain question answering [PDF] from 137.132.14.55SUNREN XU – 2006 – 137.132.14.55 … Passage retrieval (Step 2) greatly affects the performance of a QA system. If a passage retrieval module returns too many irrelevant passages, the answer extraction module is likely to fail to pinpoint the correct answer due to too much noise. Also, a … Related articles – All 5 versions
[PDF] Enhancing factoid question answering using frame semantic-based approaches [PDF] from ballarat.edu.auB Ofoghi – 2009 – researchonline.ballarat.edu.au Page 1. ENHANCING FACTOID QUESTION ANSWERING USING FRAME SEMANTIC-BASED APPROACHES DISSERTATION Submitted at the Graduate School of Information Technology and Mathematical Sciences of University … Related articles – View as HTML – Library Search – All 5 versions
Overview of the clef 2008 multilingual question answering track [PDF] from psu.eduP Forner, A Peñas, E Agirre, I Alegria… – Evaluating Systems for …, 2009 – Springer Page 1. C. Peters et al. (Eds.): CLEF 2008, LNCS 5706, pp. 262-295, 2009. (c) Springer-Verlag Berlin Heidelberg 2009 Overview of the Clef 2008 Multilingual Question Answering Track Pamela Forner1, Anselmo Peñas2, Eneko … Cited by 35 – Related articles – All 18 versions
Arabic named entity recognition [PDF] from upv.esY Benajiba – 2009 – dspace.cc.upv.es Page 1. Universidad Politécnica de Valencia Departamento de Sistemas Informáticos y Computación Reconocimiento de Formas e Inteligencia Artificial Arabic Named Entity Recognition The accepted dissertation of Yassine Benajiba in partial fulfillment of the requirements … Cited by 2 – Related articles – All 14 versions
Bootstrapping named entity resources for adaptive question answering systems [PDF] from uc3m.esP Sánchez – 2010 – e-archivo.uc3m.es Page 1. Universidad Carlos III de Madrid Escuela Politecnica Superior Tesis Doctoral Departamento de Informática Bootstrapping Named Entity Resources for Adaptive Question Answering Systems Leganés, Julio de 2010 Autor: César de Pablo Sánchez … Related articles – All 7 versions
[PDF] Using minimal recursion semantics in Japanese question answering [PDF] from dridan.comR Dridan – 2006 – dridan.com … in Section 2.7. Passage Retrieval The passage retrieval module takes information from the question processing stage … Instead of implementing or sourcing a passage retrieval module, I will use what is termed ‘oracle IR’ for the evaluations. … Cited by 2 – Related articles – View as HTML – Library Search – All 8 versions
[PDF] QA+ ML@ Wikipedia&Google [PDF] from utl.ptJPCG Silva – 2009 – dspace.ist.utl.pt … formed into a representation that can be used by the Passage Retrieval module to retrieve passages that can contain possible answers4. … 2.2.2 Passage retrieval The goal of the passage retrieval module is to find relevant documents 14 from a given collection. A … Cited by 1 – Related articles – View as HTML – All 3 versions
Experiencia Mexicana en la Búsqueda de Respuestas en Español [PDF] from unam.mxA LÓPEZ LÓPEZ, M MONTES Y GÓMEZ… – Computación y …, 2009 – ojs.unam.mx Page 1. Mexican Experience in Spanish Question Answering Experiencia Mexicana en la Búsqueda de Respuestas en Español Manuel Montes y Gómez, Luis Villaseñor Pineda and Aurelio López López Laboratorio de Tecnologías … All 8 versions
[PDF] PROBABILISTIC RELAXED UNIFICATION FORMALISM AND [PDF] from abou-assaleh.netT Abou-Assaleh – 2008 – tony.abou-assaleh.net Page 1. PROBABILISTIC RELAXED UNIFICATION FORMALISM AND ITS APPLICATION IN QUESTION ANSWERING by Tony Abou-Assaleh Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at … Related articles – View as HTML
[PDF] Developing Cross Language Systems for Language Pair with Limited Resource-Indonesian-Japanese CLIR and CLQA [PDF] from tut.ac.jpA Purwarianti – 2007 – slp.ics.tut.ac.jp Page 1. Developing Cross Language Systems for Language Pair with Limited Resource -Indonesian-Japanese CLIR and CLQA- December, 2007 DOCTOR OF ENGINEERING Ayu Purwarianti Toyohashi University of Technology Page 2. Page 3. … Related articles – View as HTML
[PDF] In Search of the Why [PDF] from ru.nlS Verberne – 2010 – lands.let.ru.nl … RQ III. To what extent can we improve answer ranking by adding structural linguistic information to a passage retrieval module for why-QA and which information from the question and its candidate answers is the most important? … Cited by 1 – Related articles – View as HTML – All 4 versions
[PDF] Toponym Disambiguation in Natural Language Processing [PDF] from upv.esD Buscaldi – 2010 – dsic.upv.es … 6.1 The SemQUASAR QA System . . . . . 99 6.1.1 Question Analysis Module . . . . . 99 6.1.2 The Passage Retrieval Module . . . . . 101 6.1.3 WordNet-based Indexing . . . . . 103 6.1.4 Answer Extraction . . . . . … Related articles – View as HTML
Soft matching for question answering [PDF] from nus.eduH Cui – 2006 – scholarbank.nus.edu Page 1. Soft Matching for Question Answering Hang Cui Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the School of Computing NATIONAL UNIVERSITY OF SINGAPORE 2006 Page 2. c?2006 Hang Cui All Rights Reserved Page 3. … Cited by 2 – Related articles – All 12 versions
Automatic Methods To Disambiguate Geospatial Queries [PDF] from mtholyoke.eduC Hafernik – 2011 – ida.mtholyoke.edu Page 1. I give permission for public access to my thesis and for any copying done at the discretion of the archives librarian and/or the College librarian …………… June 25, 2007 Carolyn T. Hafernik Page 2. Automatic Methods To Disambiguate Geospatial Queries … Related articles – All 4 versions
[PDF] MULTILINGUAL RESTRICTED DOMAIN QA SYSTEM WITH DIALOGUE MANAGEMENT (BENGALI AND TELUGU AS A CASE STUDY) [PDF] from parthapakray.comP PAKRAY – 2007 – parthapakray.com … answers in several documents are not useful. Furthermore, a highly accurate passage retrieval module is required, because frequently the answer occurs in a very small set of passages. • RDQA systems are frequently task-based. So, the repertory of question … Related articles – View as HTML – All 3 versions
[PDF] Advanced Patent Document Processing Techniques [PDF] from upf.eduR To… – Month, 2006 – recerca.upf.edu Page 1. FP6-028116 D8.1 Overview of the state of the art PATEXPERT FP6-028116 Advanced Patent Document Processing Techniques State of the Art in Patent Processing Due date of deliverable: 30 April 2006 Actual submission date: 9 May 2006 … Related articles – View as HTML – All 3 versions