349,546 Hits in 8.2 sec

Answer extraction, semantic clustering, and extractive summarization for clinical question answering

Dina Demner-Fushman, Jimmy Lin
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
This paper presents a hybrid approach to question answering in the clinical domain that combines techniques from summarization and information retrieval.  ...  Two evaluations-a manual one focused on short answers and an automatic one focused on the supporting abstracts-demonstrate that our system compares favorably to PubMed, the search system most widely used  ...  Question Answering Approach Conflicting desiderata shape the characteristics of "answers" to clinical questions. On the one hand, conciseness is paramount.  ... 
doi:10.3115/1220175.1220281 dblp:conf/acl/Demner-FushmanL06 fatcat:2azk2kzycfd7fdzmfdlm3xc6vq

DalTREC 2005 QA System Jellyfish: Mark-and-Match Approach to Question Answering

Tony Abou-Assaleh, Nick Cercone, Jon Doyle, Vlado Keselj, Chris Whidden
2005 Text Retrieval Conference  
Three runs were submitted for the Question Answering track.  ...  Our approach was based on a mark-and-match methodology with regular expression rewriting.  ...  In particular, we are working on incorporating shallow semantic parsing of the candidate answers in order to rank them.  ... 
dblp:conf/trec/Abou-AssalehCDKW05 fatcat:fcvzxhcelrf3tmryq6o43t4dxi

UofL at TAC 2008 Update Summarization and Question Answering

Yllias Chali, Sadid A. Hasan, Shafiq R. Joty
2008 Text Analysis Conference  
In this paper, we describe our update summarization and question answering (QA) systems participated in the TAC 2008 competition.  ...  On the other hand, the question answering system is built on our previous system participated in TREC 2007 QA track with different approach followed for the squishy list type questions.  ...  Acknowledgements This work was supported by the Natural Sciences and Engineering Research Council (NSERC) research grant and the University of Lethbridge.  ... 
dblp:conf/tac/ChaliHJ08 fatcat:qo7vr5yd7vb5njliv6e7zgzsbi

A new approach to unsupervised text summarization

Tadashi Nomoto, Yuji Matsumoto
2001 Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '01  
The paper presents a novel approach to unsupervised text summarization.  ...  represent their source documents in IR tasks such document retrieval and text categorization.  ...  DIVERSITY-BASED SUMMARIZATION Assuming that the problem of summarization is one of finding a subset of sentences in text which in some way represents its source text, a natural question to ask is, 'what  ... 
doi:10.1145/383952.383956 dblp:conf/sigir/NomotoM01 fatcat:uou7z2ox5rdbjn4kyuhy6tvhgu

MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization [article]

Canwen Xu and Jiaxin Pei and Hongtao Wu and Yiyu Liu and Chenliang Li
2020 arXiv   pre-print
We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization.  ...  Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question answering, and summarization.  ...  first large-scale dataset covering three major NLP tasks: text classification, question answering and summarization.  ... 
arXiv:2004.12302v2 fatcat:gbp2eycmlvejrdlnfqim277znu

FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization [article]

Esin Durmus and He He and Mona Diab
2020 arXiv   pre-print
Given question-answer pairs generated from the summary, a QA model extracts answers from the document; non-matched answers indicate unfaithful information in the summary.  ...  Neural abstractive summarization models are prone to generate content inconsistent with the source document, i.e. unfaithful. Existing automatic metrics do not capture such mistakes effectively.  ...  Acknowledgement We would like to thank Faisal Ladhak, the Lex and Comprehend groups at Amazon Web Services AI, and the anonymous reviewers for their feedback on this work.  ... 
arXiv:2005.03754v1 fatcat:i5mfv7isnnddfmir4wfuxew7zu

Automatic Summarization System coupled with a Question-Answering System (QAAS) [article]

Juan-Manuel Torres-Moreno and Pier-Luc St-Onge and Michel Gagnon and Marc El-Bèze and Patrice Bellot
2009 arXiv   pre-print
This technique might improve a Question-Answering system, whose function is to provide an exact answer to a question in natural language.  ...  Our results on French corpus demonstrate that the coupling of Automatic Summarization system with a Question-Answering system is promising.  ...  We also thank Sinequa for providing the labeled corpus containing Named Entities and the translation of the questions.  ... 
arXiv:0905.2990v1 fatcat:iycgx5wonbcnvkr54dmmzdksoa

The diversity-based approach to open-domain text summarization

Tadashi Nomoto, Yuji Matsumoto
2003 Information Processing & Management  
The paper introduces a novel approach to unsupervised text summarization, which in principle should work for any domain or genre.  ...  The paper also addresses the question of how closely the diversity approach models human judgments on summarization.  ...  The diversity-based summarization Assuming that the problem of summarization is one of finding a subset of sentences in text which in some way represents its source text, a natural question to ask is,  ... 
doi:10.1016/s0306-4573(02)00096-1 fatcat:oyxpckkxubhu7c25qyyd6igaoq

Text-to-Text Generation for Question Answering [chapter]

Wauter Bosma, Erwin Marsi, Emiel Krahmer, Mariët Theune
2011 Interactive Multi-modal Question-Answering  
When answering questions, major challenges are (a) to carefully determine the content of the answer and (b) phrase it in a proper way.  ...  In IMIX, we focus on two text-to-text generation techniques to accomplish this: content selection and sentence fusion.  ...  To this end, we devised a framework for automatic summarization which is founded on graph theory and can be applied as a text-to-text generation technique in question answering.  ... 
doi:10.1007/978-3-642-17525-1_6 dblp:series/tanlp/BosmaMKT11 fatcat:vy4eds74lfbk3jcps23aj3xwzm

Relation Extraction for Open and Closed Domain Question Answering [chapter]

Gosse Bouma, Ismail Fahmi, Jori Mur
2011 Interactive Multi-modal Question-Answering  
One of the most accurate methods in Question Answering uses off-line information extraction to find answers for frequently asked questions.  ...  This method works well for large text collections and for seeds which are easily identified, such as named entities, and is well-suited for open domain question answering.  ...  Question answering is the task of finding answers to user questions in (large) text collections.  ... 
doi:10.1007/978-3-642-17525-1_8 dblp:series/tanlp/BoumaFM11 fatcat:jkoly4jsljaxfgfky3xs547j3i

A survey on sentimental cluster based opinion summarization in question answering community

Ankur Goswami
2019 International Journal of Advanced Technology and Engineering Exploration  
Conflicts of interest The author has no conflicts of interest to declare.  ...  Question answer community on social networks and many more. 4.Suggested approach The entire procedure of our suggested approach for the summarization task involves following phases: clustering, classification  ...  , learning model designed to measure the answerability of questions to a product review.  ... 
doi:10.19101/ijatee.2019.650016 fatcat:zxuraar6azfctfhhzrnjqoro3a

Tweet Contextualization (Answering Tweet Question) - the Role of Multi-document Summarization

Pinaki Bhaskar, Somnath Banerjee, Sivaji Bandyopadhyay
2013 Conference and Labs of the Evaluation Forum  
In our system there are three major sub-systems; i) Offline multi-document summarization, ii) Focused IR and iii) online multi-document Summarization.  ...  The Offline multi-document summarization system is based on document graph, clustering and sentence compression. In the Focused IR system, Wikipedia documents are indexed using Lucene with NE field.  ...  We acknowledge the support of the Department of Electronics and Information Technology (DeitY), Ministry of Communications & Information Technology (MCIT), Government of India funded project "Development  ... 
dblp:conf/clef/BhaskarBB13 fatcat:bdhrsixvhjft3jcitffjjad2f4

Real, Live, and Concise: Answering Open-Domain Questions with Word Embedding and Summarization

Rana Malhas, Marwan Torki, Rahma Ali, Tamer Elsayed, Evi Yulianti
2016 Text Retrieval Conference  
Answers, Google Search, and Bing Search), answer ranking using learning to rank models, and summarization of top ranked answers.  ...  A main objective of those systems is to harness the plethora of existing answered questions; hence transforming the problem to finding good answers to newlyposed questions from similar previously-answered  ...  Answers questions and their corresponding available answers.  ... 
dblp:conf/trec/MalhasTAEY16 fatcat:4to7dplp3fc5fc3ljzpy2zy3ui

CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization [article]

Andre Esteva, Anuprit Kale, Romain Paulus, Kazuma Hashimoto, Wenpeng Yin, Dragomir Radev, Richard Socher
2020 arXiv   pre-print
The ranker is composed of a multi-hop question-answering module, that together with a multi-paragraph abstractive summarizer adjust retriever scores.  ...  answers during a time of crisis.  ...  SLEDGE [14] extends this by using SciBERT [3] , also fine-tuned on MS MARCO, to re-rank articles retrieved with BM25. Question Answering and Text Summarization.  ... 
arXiv:2006.09595v1 fatcat:2wctjpxfnbfdtciynysotuluku

Vidiam: Corpus-based Development of a Dialogue Manager for Multimodal Question Answering [chapter]

Boris van Schooten, Rieks op den Akker
2011 Interactive Multi-modal Question-Answering  
Since research in Question Answering Dialog for multi-modal information retrieval is still new, no suitable corpora were available to base a system on.  ...  The approach that was followed is data-driven, that is, corpus-based.  ...  ones) to disambiguate the anaphors and other references in the question text.  ... 
doi:10.1007/978-3-642-17525-1_3 dblp:series/tanlp/SchootenA11 fatcat:6b7h3vzedfewhiixw3l5cfo5ze
« Previous Showing results 1 — 15 out of 349,546 results