Filters








111 Hits in 6.2 sec

A System for Answering Non-Factoid Japanese Questions by Using Passage Retrieval Weighted Based on Type of Answer

Masaki Murata, Sachiyo Tsukawaki, Toshiyuki Kanamaru, Qing Ma, Hitoshi Isahara
2007 NTCIR Conference on Evaluation of Information Access Technologies  
We constructed a system for answering non-factoid Japanese questions. We used passage retrieval methods for the system.  ...  We extracted paragraphs based on terms from an input question and output them as the desired answer. We classified the non-factoid questions into six categories.  ...  Acknowledgements We are grateful to all the organizers of NTCIR 6 who gave us a chance to participate in the NT-CIR 6 contest to examine and improve our questionanswering system.  ... 
dblp:conf/ntcir/MurataTKMI07 fatcat:mxvbv76xozd7dlngrf67hwppgy

JAVELIN III: Answering Non-Factoid Questions in Japanese

Hideki Shima, Teruko Mitamura
2007 NTCIR Conference on Evaluation of Information Access Technologies  
To establish a baseline Japaneseto-Japanese non-factoid question answering system, we performed the minimum extensions to our factoid question answering system.  ...  In this paper, we describe our adaptation of the JAVELIN system to Japanese question answering for the NTCIR-6 QAC track.  ...  Acknowledgment This work was supported in part by the Disruptive Technologies Office (DTO)'s Advanced Question Answering for Intelligence (AQUAINT) Program.  ... 
dblp:conf/ntcir/ShimaM07 fatcat:oq3lj6vzk5du3hf4x7lqnkxrvy

A Monolithic Approach and a Type-by-Type Approach for Non-Factoid Question-answering - Yokohama National University at NTCIR-6 QAC

Tatsunori Mori, Mitsuru Sato, Madoka Ishioroshi, Yugo Nishikawa, Shigenori Nakano, Kei Kimura
2007 NTCIR Conference on Evaluation of Information Access Technologies  
First one has a monolithic architecture that retrieves answer passages related to a question using lexical chain.  ...  Each of two approaches is based on a common hypothesis that the appropriateness of answer candidate for non-factoid questions can be measured by the combination of a) appropriateness of writing style and  ...  This study was partially supported by Grant-in-Aid for Scientific Research on Priority Areas (No.18049031 and No.19024033) from the Ministry of Education, Culture, Sports, Science and Technology, Japan  ... 
dblp:conf/ntcir/MoriSINNK07 fatcat:ivfhru2ggfec3hycf32bxbthxu

Arabic Question Answering Systems: Gap Analysis

Mariam M. Biltawi, Sara Tedmori, Arafat Awajan
2021 IEEE Access  
A generating question system is the opposite of a QA system; i.e., a generating question system generates questions for given passages by exploiting knowledge bases [2] .  ...  "using" ‫.)باستخدام(‬ The retrieved top documents are divided into passages, and a check for question focus is performed, giving 1 as a weight for each passage containing the question focus and 0 for  ... 
doi:10.1109/access.2021.3074950 fatcat:zsjkex2ylfa5hgg3qjedhqsce4

WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval [article]

Daniel Cohen, Liu Yang, W. Bruce Croft
2018 arXiv   pre-print
In this paper, we introduce a new Wikipedia based collection specific for non-factoid answer passage retrieval containing thousands of questions with annotated answers and show benchmark results on a variety  ...  With the rise in mobile and voice search, answer passage retrieval acts as a critical component of an effective information retrieval system for open domain question answering.  ...  ACKNOWLEDGEMENTS This work was supported in part by the Center for Intelligent Information Retrieval, in part by NSF #IIS-1160894, and in part by NSF grant #IIS-1419693.  ... 
arXiv:1805.03797v1 fatcat:q3a6yszqbnc7tgtjbtr6nrgvnq

Employing Two Question Answering Systems in TREC 2005

Sanda M. Harabagiu, Dan I. Moldovan, Christine Clark, Mitchell Bowden, Andrew Hickl, Patrick Wang
2005 Text Retrieval Conference  
This work, as our broader research in QA is supported by the Advanced Research Development Activity (ARDA)'s Advanced Question Answering for Intelligence (AQUAINT) Program.  ...  Acknowledgements We would like to thank the researchers and engineers from Language Computer Corporation for their valuable contributions to this work.  ...  In this strategy, decomposed questions are sent to an Answer Type Term Detection module used in PALANTIR's factoid Q/A system.  ... 
dblp:conf/trec/HarabagiuMCBHW05 fatcat:53wbfvf4t5f43m5le4fqtl7krq

Answering Any Class of Japanese Non-factoid Question by Using the Web and Example Q&A Pairs from a Social Q&A Website

Tatsunori Mori, Mitsuru Sato, Madoka Ishioroshi
2008 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology  
In this paper, we propose a method of non-factoid Web question-answering that can uniformly deal with any class of Japanese non-factoid question by using a large number of example Q&A pairs.  ...  Instead of preparing classes of questions beforehand, the method retrieves already asked question examples similar to a submitted question from a set of Q&A pairs.  ...  This study was partially supported by Grant-in-Aid for Scientific Research on Priority Areas (No.19024033) from the Ministry of Education, Culture, Sports, Science and Technology, Japan.  ... 
doi:10.1109/wiiat.2008.201 dblp:conf/webi/MoriSI08 fatcat:jt7dydg7yjhqlnxmqr6vlunlyu

Analyzing Linguistic Features for Answer Re-Ranking of Why-Questions

Manvi Breja, Sanjay Kumar Jain
2022 Journal of Cases on Information Technology  
Why-type non-factoid questions are ambiguous and involve variations in their answers.  ...  Further, answer is validated by matching the answer type of answer candidate and returns the highest ranked answer candidate with matched answer type to a user.  ...  Table 2 below compares the performance of research works on answer re-ranker of Non-factoid question answering systems.  ... 
doi:10.4018/jcit.20220701.oa10 fatcat:rd2wqn3p2ndadnh4qhqqmmta2i

A Survey on Why-Type Question Answering Systems [article]

Manvi Breja, Sanjay Kumar Jain
2019 arXiv   pre-print
Question Answering Systems reduce the time taken to get an answer, to a query asked in natural language by providing the one most relevant answer.  ...  The paper presents a survey on Why-type Question Answering System, details the architecture, the processes involved in the system and suggests further areas of research.  ...  Many researches have proposed a lot of taxonomies based on different factors for factoid type QA while limited work has been done in non-factoid QA.  ... 
arXiv:1911.04879v1 fatcat:wdvngfqkqvgfvmjn67adebwtqi

Bootstrap Pattern Learning for Open-Domain CLQA

Hideki Shima, Teruko Mitamura
2010 NTCIR Conference on Evaluation of Information Access Technologies  
We describe Javelin, a Cross-lingual Question Answering system which participated in the NTCIR-8 ACLIA evaluation and which is designed to work on any type of question, including factoid and complex questions  ...  The key technical contribution of this paper is a minimally supervised bootstrapping approach to generating lexicosyntactic patterns used for answer extraction.  ...  INTRODUCTION LTI's Javelin is a Cross-lingual Question Answering (QA) system for any type, of question, including factoid and complex questions.  ... 
dblp:conf/ntcir/ShimaM10 fatcat:rbapzevsdzfmjjey2vtmyzvp3m

Semantic Extensions of the Ephyra QA System for TREC 2007

Nico Schlaefer, Jeongwoo Ko, Justin Betteridge, Manas A. Pathak, Eric Nyberg, Guido Sautter
2007 Text Retrieval Conference  
A novel answer type classifier combines a statistical model and hand-coded rules to predict the answer type based on syntactic and semantic features of the question.  ...  Existing syntactic answer extraction approaches for factoid and list questions have been complemented with a high-accuracy semantic approach that generates a semantic representation of the question and  ...  This work was supported in part by the AQUAINT program under grant NBCHC040164.  ... 
dblp:conf/trec/SchlaeferKBPNS07 fatcat:5d77t2uaineodlrbiuhjdtxlaq

Different Facets of Text Based Automated Question Answering System

vaishali Singh
2018 International Journal for Research in Applied Science and Engineering Technology  
Finally, a summarized representation of these facets based on certain features of QA system has been done, to bring an insight for the future research.  ...  One of those information retrieval technologies is Question Answering (QA), a research field that has emerged at the intersection of information retrieval and natural language processing techniques, which  ...  ., [32] aimed at non-factoid question-answering that usually expects passages as answers.  ... 
doi:10.22214/ijraset.2018.1017 fatcat:z2l3qicgvjawpcahqyr3alk3wy

Why Question Answering using Sentiment Analysis and Word Classes

Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Takuya Kawada, Stijn De Saeger, Jun'ichi Kazama, Yiou Wang
2012 Conference on Empirical Methods in Natural Language Processing  
over a baseline state-of-the-art QA system that achieved the best performance in a shared task of Japanese non-factoid QA in NTCIR-6.  ...  In this paper we explore the utility of sentiment analysis and semantic word classes for improving why-question answering on a large-scale web corpus.  ...  http://lucene.apache.org/solr 3 To the best of our knowledge, few Japanese non-factoid QA systems in the literature have used such a large-scale corpus.4 The length of acceptable answer candidates for  ... 
dblp:conf/emnlp/OhTHKSKW12 fatcat:5sxl5xz5njb6xbltejvhzzb7gq

Joint question clustering and relevance prediction for open domain non-factoid question answering

Snigdha Chaturvedi, Vittorio Castelli, Radu Florian, Ramesh M. Nallapati, Hema Raghavan
2014 Proceedings of the 23rd international conference on World wide web - WWW '14  
An important step in this direction is to automatically infer the type of answer implied by the question, e.g., factoids, statements on a topic, instructions, reviews, etc.  ...  All three models perform better than a baseline relevance model that uses explicit Answer Type categories predicted by a supervised Answer-Type classifier, on a newsgroups dataset.  ...  Salim Roukos for his valuable suggestions and for providing the necessary resources for developing labeled data for relevance as well as for answer-types.  ... 
doi:10.1145/2566486.2567999 dblp:conf/www/ChaturvediCFNR14 fatcat:ehmzr6g6ujatjplzirf65uumga

Selecting Answers with Structured Lexical Expansion and Discourse Relations LIMSI's Participation at QA4MRE 2013

Martin Gleize, Brigitte Grau, Van-Minh Pho, Anne-Laure Ligozat, Gabriel Illouz, Frédéric Gianetti, Loïc Lahondes
2013 Conference and Labs of the Evaluation Forum  
Relation recognition shows promising results, however it has to be improved to have an impact on answer selection. The second method is based on semantic variations.  ...  We explored the English Wiktionary to find reformulations of words in the definitions, and used these reformulations to index the documents and select passages in the Entrance exams task.  ...  We kept the Factoid questions subclasses based on the expected answer type in terms of named entity type: person, organization, location, date...  ... 
dblp:conf/clef/GleizeGPLIGL13 fatcat:v3mqjksltvevzjaneyakoxscim
« Previous Showing results 1 — 15 out of 111 results