Filters








16,730 Hits in 6.2 sec

Answer Extraction for Why Arabic Questions Answering Systems: EWAQ [article]

Fatima T. AL-Khawaldeh
2019 arXiv   pre-print
The goal of the proposed system in this research is to extract answers from re-ranked retrieved passages which are retrieved by search engines. This system extracts the answer only to why questions.  ...  In EWAQ experiments, it is showed that the accuracy is increased by implementing the textual entailment in re-raking the retrieved relevant passages by search engines and deciding the correct answer.  ...  If the retrieved passage consists of more than sentence, the text is split into sentences based on the existence of dot (.). 3.  ... 
arXiv:1907.04149v1 fatcat:of3loneohzayhlz4yzyy3kqtsu

EXCERPT — a Within-Document Retrieval System Using Summarization Techniques

Jürgen Reischer
2021 Zenodo  
Segments of sentence to paragraph size can be retrieved, assembled to greater passages and ranked by informativeness.  ...  A new approach to within-document retrieval is presented using methods of automatic summarizing.  ...  Within-document retrieval is most similar to the first and second point: search in an isolated document given some search terms to retrieve passages of any length (sentences, paragraphs, chapters etc.)  ... 
doi:10.5281/zenodo.5503631 fatcat:wwva5jdb3bfpbgedig6xi73as4

Beyond Factoid QA: Effective Methods for Non-factoid Answer Sentence Retrieval [chapter]

Liu Yang, Qingyao Ai, Damiano Spina, Ruey-Cheng Chen, Liang Pang, W. Bruce Croft, Jiafeng Guo, Falk Scholer
2016 Lecture Notes in Computer Science  
Retrieving finer grained text units such as passages or sentences as answers for non-factoid Web queries is becoming increasingly important for applications such as mobile Web search.  ...  Results show that features used previously to retrieve topical sentences and factoid answer sentences are not sufficient for retrieving answer sentences for non-factoid queries, but with semantic and context  ...  Any opinions, findings and conclusions expressed in this material are those of the authors and do not necessarily reflect those of the sponsor.  ... 
doi:10.1007/978-3-319-30671-1_9 fatcat:asb4l5sdfbgclkdnmto76knmcq

Finding needles in the haystack: Search and candidate generation

J. Chu-Carroll, J. Fan, B. K. Boguraev, D. Carmel, D. Sheinwald, C. Welty
2012 IBM Journal of Research and Development  
In the IBM Watsoni system, these hypotheses are potential answers to Jeopardy!i questions and are generated by two components: search and candidate generation.  ...  The search component retrieves content relevant to a given question from Watson's knowledge resources.  ...  and the committee of the IEEE Conference on Software Science, Technology, and Engineering (SWSTE).  ... 
doi:10.1147/jrd.2012.2186682 fatcat:4yytkyt4dbhovhorh2rhr22ehi

ReQA: An Evaluation for End-to-End Answer Retrieval Models [article]

Amin Ahmad, Noah Constant, Yinfei Yang, Daniel Cer
2019 arXiv   pre-print
However, retrieving relevant answers from a huge corpus of documents is still a challenging problem, and places different requirements on the model architecture.  ...  In this paper, we introduce Retrieval Question-Answering (ReQA), a benchmark for evaluating large-scale sentence-level answer retrieval models.  ...  Acknowledgments We thank our teammates from Descartes and other Google groups for their feedback and suggestions. We would like to recognize Javier Snaider, Igor Krivokon and Ray Kurzweil.  ... 
arXiv:1907.04780v2 fatcat:vfykkz2lm5bfxoo3awpfnxzrsq

Question Answering in Spanish [chapter]

José L. Vicedo, Ruben Izquierdo, Fernando Llopis, Rafael Muñoz
2004 Lecture Notes in Computer Science  
This paper describes the architecture, operation and results obtained with the Question Answering prototype for Spanish developed in the Department of Language Processing and Information Systems at the  ...  University of Alicante for the CLEF 2003 Spanish monolingual QA evaluation task.  ...  These passages are made up of text snippets of 2 sentences. Second, the same keyword list (without lemmatisation) is input to the Google Internet search engine.  ... 
doi:10.1007/978-3-540-30222-3_52 fatcat:vxcsr623gvabpp5pp7zezx7sci

Current research in focused retrieval and result aggregation

Andrew Trotman, Shlomo Geva, Jaap Kamps, Mounia Lalmas, Vanessa Murdock
2010 Information retrieval (Boston)  
They include descriptions of live result aggregation systems, and experimental focussed retrieval systems including sentence retrieval, question answering, and entity ranking; as well as metrics for passage  ...  Both focused retrieval and result aggregation provide the user with answers to their information needs, rather than just pointers to whole documents.  ...  There are four main forms of focused retrieval: element retrieval, passage retrieval, question answering, and entity retrieval.  ... 
doi:10.1007/s10791-010-9137-5 fatcat:mrllv6ewm5bg3bq2bz73xvm4ca

Arabic Question Answering Systems: Gap Analysis

Mariam M. Biltawi, Sara Tedmori, Arafat Awajan
2021 IEEE Access  
Most of the QA systems used search engines to implement document retrieval and created a local dataset for passage retrieval.  ...  In each of the top five candidate passages, passages consisting of multiple sentences are split into single sentences.  ... 
doi:10.1109/access.2021.3074950 fatcat:zsjkex2ylfa5hgg3qjedhqsce4

A Hybrid Question Answering System

Waheeb Ahmed, P. Babu Anto
2019 Current Journal of Applied Science and Technology  
It make use of other relevant text data, outside the KB, which could enrich the available information.  ...  Text-to-KB uses web search results to identify question topic entities, map question words to KB predicates, and enhance the features of the candidates obtained from the KB.  ...  Online Module The online module searches text to find answers. The online module performs four tasks ( Fig. 1) : first is question classification. and; the second is the passage retriever.  ... 
doi:10.9734/cjast/2019/v34i330129 fatcat:g3hnnq6syffirezy2frulsph6y

Utilizing sub-topical structure of documents for information retrieval

Debasis Ganguly, Johannes Leveling, Gareth J.F. Jones
2011 Proceedings of the 4th workshop on Workshop for Ph.D. students in information & knowledge management - PIKM '11  
For example, for scoring a document by combining the retrieval scores of its constituent segments, exploiting the proximity of query terms in documents for ad-hoc search, and for question answering (QA  ...  ), where retrieved passages from multiple documents are aggregated and presented as a single document to a searcher.  ...  Acknowledgments This research is supported by the Science Foundation Ireland (Grant 07/CE/I1142) as part of the Centre for Next Generation Localisation (CNGL).  ... 
doi:10.1145/2065003.2065019 dblp:conf/cikm/GangulyLJ11 fatcat:bywv22zyynbklalkdlbzn2xs5q

AskHERMES: An online question answering system for complex clinical questions

YongGang Cao, Feifan Liu, Pippa Simpson, Lamont Antieau, Andrew Bennett, James J. Cimino, John Ely, Hong Yu
2011 Journal of Biomedical Informatics  
Five types of resources were indexed in this system: MEDLINE abstracts, PubMed Central full-text articles, eMedicine documents, clinical guidelines and Wikipedia articles.  ...  Measurement-We compared the AskHERMES system with Google (Google and Google Scholar) and UpToDate and asked physicians to score the three systems by ease of use, quality of answer, time spent, and overall  ...  Any opinions, findings, or recommendations are those of the authors and do not necessarily reflect the views of the NIH.  ... 
doi:10.1016/j.jbi.2011.01.004 pmid:21256977 pmcid:PMC3433744 fatcat:4dvcfiiusfhrznzcdicvtlxjpi

Experiments in Passage Selection and Answer Identification for Question Answering [chapter]

Horacio Saggion, Robert Gaizauskas
2006 Lecture Notes in Computer Science  
In such an approach two main problems need to be addressed to reduce the search space: better selecting answer bearing passages in the document retrieval step and better pinpointing answers in the answer  ...  We investigate the effect of word-based and linguistic-based features for the identification of answer-bearing sentences and answer candidates in a QA system and show that both play a significant role.  ...  The Text REtrieval Conferences (TREC) [Voorhees, 2002] have clearly defined question types, data, and evaluation methods to assess the performance of QA systems.  ... 
doi:10.1007/11816508_30 fatcat:qi3wwm4m3babxiv7oxohsyiyxy

A weighted string pattern matching-based passage ranking algorithm for video question answering

Y WU, J YANG, Y LEE
2008 Expert systems with applications  
, and answer pattern recall rates.  ...  Users interact with our videoQA system through natural language questions, while our system returns passage fragments with corresponding video clips as answers.  ...  By means of text retrieval technology, the search space can be largely reduced and limited in a small set of relevant document.  ... 
doi:10.1016/j.eswa.2007.04.008 fatcat:hn7sv3h6ybcqpge5page3rxdii

Using a Passage Retrieval System to Support Question Answering Process [chapter]

Fernando Llopis, José Luis Vicedo, Antonio Ferrández
2002 Lecture Notes in Computer Science  
This kind of IR systems is usually called Passage Retrieval (PR). This paper discusses the use of our PR system in the question answering process (QA).  ...  Previous works in Information Retrieval show that using pieces of text obtain better results than using the whole document as the basic unit to compare with the user's query.  ...  This fact allows reducing QA systems computational complexity (they work on small fragments of text instead of documents) and improves QA's precision, since the passage list retrieved is more relevant  ... 
doi:10.1007/3-540-46043-8_5 fatcat:vmpqewavdbbjjka7etq6l4aqta

A logical representation of Arabic questions toward automatic passage extraction from the Web

Wided Bakari, Patrice Bellot, Mahmoud Neji
2017 International Journal of Speech Technology  
And then, the results of passages of texts that are automatically generated achieved an 87% score for accuracy and a 98% score for c@1.  ...  Next, it is essential to retrieve a passage from the web that can serve as an appropriate answer.  ...  The snapshot of these components has been shown below. Answer passage retrieval Passage retrieval is a way to query the Web to retrieve a passage that answers a given question.  ... 
doi:10.1007/s10772-017-9411-7 fatcat:u7wsti7bgrb43jt6auaawy4ziy
« Previous Showing results 1 — 15 out of 16,730 results