Filters








24,206 Hits in 6.4 sec

Interactive Cross-Language Question Answering: Searching Passages Versus Searching Documents [chapter]

Fernando López-Ostenero, Julio Gonzalo, Víctor Peinado, Felisa Verdejo
2005 Lecture Notes in Computer Science  
iCLEF 2004 is the first comparative evaluation of interactive Cross-Language Question Answering systems.  ...  versions of the documents; the contrastive system is identical, but searching passages which contain expressions of the appropriate answer type.  ...  Introduction In spite of its long name, "Interactive Cross-Language Question Answering" is not an exotic task, but rather a quite natural problem in the context of e.g. web searches: we want to know the  ... 
doi:10.1007/11519645_33 fatcat:u75qd2m4pfhsrchoejbtudoeau

iCLEF2005 at REINA-USAL: Use of Free On-line Machine Translation Programs for Interactive Cross-Language Question Answering

Ángel F. Zazo Rodríguez, Carlos G. Figuerola, José Luis Alonso Berrocal, Viviana Fernández Marcial
2005 Conference and Labs of the Evaluation Forum  
For the iCLEF experiment of CLEF 2005 at University of Salamanca, we have explored the use of free on-line machine translation (MT) programs for the interactive Cross-Language Question Answering process  ...  Our cross-language information retrieval system is a standard document retrieval system performing monolingual searches.  ...  Introduction For our participation in the interactive CLEF track we have explored the use of free on-line machine translation (MT) for the interactive Cross-Language Question Answering (CL-QA) process.  ... 
dblp:conf/clef/RodriguezFBM05 fatcat:ypbi63cnfjfpjdmizh5grecutq

Talk to Papers: Bringing Neural Question Answering to Academic Search [article]

Tianchang Zhao, Kyusong Lee
2020 arXiv   pre-print
We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search.  ...  It's designed to enable researchers to use natural language queries to find precise answers and extract insights from a massive amount of academic papers.  ...  QA dataset with cross entropy loss, i.e.  ... 
arXiv:2004.02002v3 fatcat:wa4pb3xsujavljo5q3k234cqh4

Statistical source expansion for question answering

Nico Schlaefer, Jennifer Chu-Carroll, Eric Nyberg, James Fan, Wlodek Zadrozny, David Ferrucci
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
While the expanded corpus is not intended for human consumption, it can be leveraged in question answering (QA) and other information retrieval or extraction tasks to find more relevant knowledge and to  ...  I have been fortunate to work with one of the most experienced researchers in the field of question answering, and was able to learn a lot from her about her area of expertise and about conducting rigorous  ...  Li and Meng [2003] show that document expansion can improve search performance in cross-lingual spoken document retrieval.  ... 
doi:10.1145/2063576.2063632 dblp:conf/cikm/SchlaeferCNFZF11 fatcat:whoy62klazctbdo4p57wbevkdu

Span Selection Pre-training for Question Answering [article]

Michael Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto, Lin Pan, G P Shrivatsa Bhargav, Dinesh Garg, Avirup Sil
2020 arXiv   pre-print
Span Selection Pre-Training (SSPT) poses cloze-like training instances, but rather than draw the answer from the model's parameters, it is selected from a relevant passage.  ...  Specifically, our proposed model has strong empirical evidence as it obtains SOTA results on Natural Questions, a new benchmark MRC dataset, outperforming BERT-LARGE by 3 F1 points on short answer prediction  ...  Unlike other work, this did not use document structure but instead used a search index to retrieve a related passage for a given question.  ... 
arXiv:1909.04120v2 fatcat:nsoem2kyyfhr5l4lcogcl2vcj4

SRQA: Synthetic Reader for Factoid Question Answering

Jiuniu Wang, Wenjia Xu, Xingyu Fu, Yang Wei, Li Jin, Ziyan Chen, Guangluan Xu, Yirong Wu
2019 Knowledge-Based Systems  
The multilayer attention mechanism conducts interaction between the question and the passage within each layer, making the token representation of evidences in each layer takes the requirement of the question  ...  This model enhances the question answering system in the multi-document scenario from three aspects: model structure, optimization goal, and training method, corresponding to Multilayer Attention (MA),  ...  Introduction The Question Answering (QA) system aims to generate answers to users' questions, so the system needs to search for answers within the related passages or knowledge bases.  ... 
doi:10.1016/j.knosys.2019.105415 fatcat:agstiyiqgbeobdocsclhdtcqtu

Concept Recognition, Information Retrieval, and Machine Learning in Genomics Question-Answering

J. Gregory Caporaso, William A. Baumgartner Jr., Hyunmin Kim, Zhiyong Lu, Helen L. Johnson, Olga Medvedeva, Anna Lindemann, Lynne M. Fox, Elizabeth K. White, K. Bretonnel Cohen, Lawrence Hunter
2006 Text Retrieval Conference  
TREC Genomics 2006 presented a genomics question-answering challenge with questions on twenty-seven topics, and a corpus of 162,259 full-text biomedical journal articles from which to derive answers.  ...  We searched the passage collection for these expanded queries using the Indri search engine from the Lemur package, with pseudo-relevance feedback.  ...  Query preprocessing Our first step in generating results for each topic involved converting the question into a query to be passed to our search engine.  ... 
dblp:conf/trec/CaporasoBKLJMLFWCH06 fatcat:bmrnjm6ecjcxzb7dxvcmnvslgm

Iterative Relevance Feedback for Answer Passage Retrieval with Passage-level Semantic Match [article]

Keping Bi, Qingyao Ai, W. Bruce Croft
2018 arXiv   pre-print
and from retrieving documents to retrieving answers.  ...  In this paper, we study iterative relevance feedback techniques with a focus on retrieving answer passages.  ...  All the parameters were set using 5-fold cross-validation over all the queries in each collection with grid search.  ... 
arXiv:1812.08870v1 fatcat:fwyo536aq5eyppr3vxk4cjkaie

Biomedical question answering: A survey

Sofia J. Athenikos, Hyoil Han
2010 Computer Methods and Programs in Biomedicine  
Athenikos). cise answers to their questions, by employing Information Extraction (IE) and Natural Language Processing (NLP) techniques, instead of providing a large number of documents that are potentially  ...  of more sophisticated techniques for natural language (NL) question analysis and classification, (3) Development of effective methods for answer generation from potentially conflicting evidences, (4)  ...  Out of the retrieved and selected documents, candidate answer passages are extracted, which constitute the input for the answer processing phase.  ... 
doi:10.1016/j.cmpb.2009.10.003 pmid:19913938 fatcat:tv4sel4llbcnjppnn7g2tygqze

A survey on question answering technology from an information retrieval perspective

Oleksandr Kolomiyets, Marie-Francine Moens
2011 Information Sciences  
On the one hand, natural language queries are reduced to keyword-based searches, on the other hand, knowledge bases are queried with structured or logical queries obtained from the natural language questions  ...  It presents the question answering task from an information retrieval perspective and emphasises the importance of retrieval models, i.e., representations of queries and information documents, and retrieval  ...  Cross-language question answering may inspire cross-media question answering, where a question or statement in natural language interrogates image, video or audio archives.  ... 
doi:10.1016/j.ins.2011.07.047 fatcat:se6dcorj2jbidath35go5wi5yy

UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text [article]

Soumajit Pramanik, Jesujoba Alabi, Rishiraj Saha Roy, Gerhard Weikum
2022 arXiv   pre-print
Question answering over knowledge graphs and other RDF data has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries.  ...  Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone.  ...  This is because reading comprehension (RC) QA systems search for the best answer span within a passage, and will not work well unless the passage matches the question tokens and contains the answer.  ... 
arXiv:2108.08614v4 fatcat:yllcmsrq7jg7dptmxtpifkyzqe

Open-Domain Question–Answering

John Prager
2006 Foundations and Trends in Information Retrieval  
There are also many characteristics of answers to opinion-oriented questions that differ from those for fact-based questions [284] .  ...  Also, even a relevant opinion-bearing document may contain offtopic passages that the user may not be interested in, and so one may wish to discard such passages.  ... 
doi:10.1561/1500000001 fatcat:5xq5eb7idrb37lz3wyzfl4cb34

Bio-AnswerFinder: a system to find answers to questions from biomedical texts

2019 Database: The Journal of Biological Databases and Curation  
To improve document retrieval performance, we introduced a supervised long short term memory neural network to select keywords from the question to facilitate iterative keyword search.  ...  Our approach retrieves relevant documents iteratively via enhanced keyword queries from a traditional search engine.  ...  systems provide precise answers to natural language questions.  ... 
doi:10.1093/database/baz137 pmid:31925435 pmcid:PMC7053013 fatcat:scxluxhtd5burcx2xkebte6die

Teaching language models to support answers with verified quotes [article]

Jacob Menick, Maja Trebacz, Vladimir Mikulik, John Aslanides, Francis Song, Martin Chadwick, Mia Glaese, Susannah Young, Lucy Campbell-Gillingham, Geoffrey Irving, Nat McAleese
2022 arXiv   pre-print
Recent large language models often answer factual questions correctly.  ...  Supporting evidence is drawn from multiple documents found via a search engine, or from a single user-provided document.  ...  Katie Millican built the text scraper we used to preprocess all documents.  ... 
arXiv:2203.11147v1 fatcat:xcyia7pag5ayxmbnhbvjkzyrc4

Training Curricula for Open Domain Answer Re-Ranking [article]

Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder
2020 arXiv   pre-print
In precision-oriented tasks like answer ranking, it is more important to rank many relevant answers highly than to retrieve all relevant answers.  ...  It follows that a good ranking strategy would be to learn how to identify the easiest correct answers first (i.e., assign a high ranking score to answers that have characteristics that usually indicate  ...  For answer ranking, the question is treated as the query and answers are treated as the document.  ... 
arXiv:2004.14269v1 fatcat:7ivxm62ggbcrxnmxyccgs24nqq
« Previous Showing results 1 — 15 out of 24,206 results