42,654 Hits in 7.0 sec

Enhancing Performance with a Learnable Strategy for Multiple Question Answering Modules

Hyo-Jung Oh, Sung Hyon Myaeng, Myung-Gil Jang
2009 ETRI Journal  
A question answering (QA) system can be built using multiple QA modules that can individually serve as a QA system in and of themselves.  ...  This paper proposes a learnable, strategy-driven QA model that aims at enhancing both efficiency and effectiveness.  ...  S1 Set 5 as the cut-off value Answer selection S2 Confidence value boosting Table 4 . 4 Error distribution in strategy-driven QA.  ... 
doi:10.4218/etrij.09.0108.0388 fatcat:j3jxutzbrjax5nhlkzmcn4wbn4

Vocabulary-Driven Passage Retrieval for Question-Answering in Genomics

Julien Gobeill, Imad Tbahriti, Frédéric Ehrler, Patrick Ruch
2007 Text Retrieval Conference  
This year, our efforts concentrated on combining knowledge-driven methods on top of a standard vectorspace retrieval approach.  ...  This year, like in 2006, we use a collection of about 160000 full-text articles. The proposed task is a passage retrieval task.  ...  Acknowledgments The study reported in this paper has been supported by the SNF (EAGL project 3252B0-105755).  ... 
dblp:conf/trec/GobeillTER07 fatcat:xikbtirdg5gxldyjijowzyxr3m

An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms [article]

Kanika Narang, Chaoqi Yang, Adit Krishnan, Junting Wang, Hari Sundaram, Carolyn Sutter
2019 arXiv   pre-print
This paper addresses the question of identifying the best candidate answer to a question on Community Question Answer (CQA) forums.  ...  We show strong results over the state-of-the-art neural baselines in extensive experiments on 50 StackExchange communities.  ...  First, in Section 3.1, we introduce potential strategies for selecting the accepted answer given a question. We show how each strategy induces a graph G on the question-answer (q, a) tuples.  ... 
arXiv:1911.06957v1 fatcat:ijh5d4z76vgg5j7qqkhw2d6i24

Compositional question answering: A divide and conquer approach

Hyo-Jung Oh, Ki-Youn Sung, Myung-Gil Jang, Sung Hyon Myaeng
2011 Information Processing & Management  
The goal of the proposed QA method is to answer a composite question by dividing it into atomic ones, instead of developing an entirely new method tailored for the new question type.  ...  This paper describes how questions can be characterized for question answering (QA) along different facets and focuses on questions that cannot be answered directly but can be divided into simpler ones  ...  If it is not sufficiently high, other QA modules are invoked according to the chosen strategy for weight boosting (Oh & Myaeng, 2009 ).  ... 
doi:10.1016/j.ipm.2010.03.011 fatcat:2v6q2vivnnadxmvfdjj7dkgwky

A Multi-Strategy and Multi-Source Approach to Question Answering

Jennifer Chu-Carroll, John M. Prager, Christopher A. Welty, Krzysztof Czuba, David A. Ferrucci
2002 Text Retrieval Conference  
This work was supported in part by the Advanced Research and Development Activity (ARDA)'s Advanced Question Answering for Intelligence (AQUAINT) Program under contract number MDA904-01-C-0988.  ...  Effects of NIL Assignment In our best submission run (IBMPQSQACYC), the confidence-based NIL-assignment strategy resulted in 147 NIL answers, which was more than we anticipated.  ...  A large boost in confidence is given to identical answers proposed by both systems, whereas a small boost in confidence is given to partially overlapping answers. 3.  ... 
dblp:conf/trec/Chu-CarrollPWCF02 fatcat:3cygrsqpzngh5dbsqvnjuyixlm

Combining evidence with a probabilistic framework for answer ranking and answer merging in question answering

Jeongwoo Ko, Luo Si, Eric Nyberg
2010 Information Processing & Management  
Question answering (QA) aims at finding exact answers to a user's question from a large collection of documents.  ...  This is more challenging in multi-strategy QA, in which multiple answering agents are used to extract answer candidates.  ...  Acknowledgments This work was supported in part by ARDA/DTO Advanced Question Answering for Intelligence (AQUAINT) program award number NBCHC040164.  ... 
doi:10.1016/j.ipm.2009.11.004 fatcat:fr5zrh3fdzecva5rvm3nfjgj3e

Answer Selection in a Multi-stream Open Domain Question Answering System [chapter]

Valentin Jijkoun, Maarten de Rijke
2004 Lecture Notes in Computer Science  
We report on experiments aimed at understanding and evaluating the effect of different options for answer selection in a multi-stream question answering system.  ...  Question answering systems aim to meet users' information needs by returning exact answers in response to a question.  ...  Some answering strategies may be highly effective for certain question types, but not for others. 2.  ... 
doi:10.1007/978-3-540-24752-4_8 fatcat:dx27ks4ilzb67lhozrcfxj6fxa

Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce [article]

Yang Deng, Wenxuan Zhang, Wai Lam
2020 arXiv   pre-print
Nevertheless, the rich information about personal opinions in product reviews, which is essential to answer those product-specific questions, is underutilized in current generation-based review-driven  ...  Product-related question answering (QA) is an important but challenging task in E-Commerce.  ...  In order to attend words in reviews with decisive opinion and also alleviate the noise from irrelevant reviews, we introduce two strategies of opinion fusion to re-weight attention scores of the words  ... 
arXiv:2008.11972v2 fatcat:uncuhn3qrneo7jbdbb5by2sreq

Multiple Data Augmentation Strategies for Improving Performance on Automatic Short Answer Scoring

Jiaqi Lun, Jia Zhu, Yong Tang, Min Yang
and other features in large amounts of unsupervised data, and actually adds external knowledge.  ...  Automatic short answer scoring (ASAS) is a research subject of intelligent education, which is a hot field of natural language understanding.  ...  Acknowledgements This work is supported by the National Natural Science Foundation of China (U1811263) and the Guangzhou Key Laboratory of Big Data and Intelligent Education (201905010009).  ... 
doi:10.1609/aaai.v34i09.7062 fatcat:l4sc6lqaqvdn5oui6x5bgape7i

A Robust Adversarial Training Approach to Machine Reading Comprehension

Kai Liu, Xin Liu, An Yang, Jing Liu, Jinsong Su, Sujian Li, Qiaoqiao She
Moreover, when coupled with other data augmentation strategy, our approach further boosts the overall performance on adversarial datasets and outperforms the state-of-the-art methods.  ...  In this paper, we propose a novel robust adversarial training approach to improve the robustness of MRC models in a more generic way.  ...  We also thank Sheng Lu and the anonymous reviewers for their constructive criticism of the manuscript.  ... 
doi:10.1609/aaai.v34i05.6357 fatcat:n6k4cda5bvgobdc55q4ke4cm5i

The Conflict-Driven Answer Set Solver clasp: Progress Report [chapter]

Martin Gebser, Benjamin Kaufmann, Torsten Schaub
2009 Lecture Notes in Computer Science  
We summarize the salient features of the current version of the answer set solver clasp, focusing on the progress made since version RC4 of clasp.  ...  The robustness of clasp is boosted by advanced restart strategies.  ...  to conflict-driven nogood learning, comparing various strategies for restarts, nogood deletion, and decision heuristics.  ... 
doi:10.1007/978-3-642-04238-6_50 fatcat:p3svekro2vfnziln2udpclsequ

Automatic Coupling of Answer Extraction and Information Retrieval

Xuchen Yao, Benjamin Van Durme, Peter Clark
2013 Annual Meeting of the Association for Computational Linguistics  
Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Question Answering (QA), with repeated overengineering on IR, and not necessarily performance  ...  Our method is very quick to implement, and significantly improves IR for QA (measured in Mean Average Precision and Mean Reciprocal Rank) by 10%-20% against an uncoupled retrieval baseline in both document  ...  Queries were lightly optimized using the following strategies: Query Weighting In practice query words are weighted: #weight(1.0 When 1.0 was 1.0 Alaska 1.0 purchased α #max(#any:CD #any:DATE)) with a  ... 
dblp:conf/acl/YaoDC13 fatcat:ky4ctuof65edfj7ifhnubpa6wy

A Unified MRC Framework for Named Entity Recognition [article]

Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, Jiwei Li
2020 arXiv   pre-print
This formulation naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities for different categories requires answering two independent questions.  ...  For example, extracting entities with the per label is formalized as extracting answer spans to the question " which person is mentioned in the text?".  ...  The work is supported by the National Natural Science Foundation of China (NSFC No. 61625107 and 61751209).  ... 
arXiv:1910.11476v6 fatcat:d3342pkudfbirln2tvnltuzcd4

Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering [article]

Luxi Xing, Yue Hu, Jing Yu, Yuqiang Xie, Wei Peng
2021 arXiv   pre-print
We devise a tailoring strategy to filter extracted knowledge under monitoring of the coarse semantic of question on the knowledge extraction stage.  ...  Towards the issue of introducing related knowledge, we propose a semantic-driven knowledge-aware QA framework, which controls the knowledge injection in a coarse-to-careful fashion.  ...  Experiment results demonstrate the effectiveness of the proposed approach. Fig. 1 . 1 Workflow of Semantic-driven Knowledge-aware Question Answering (SEEK-QA) framework.  ... 
arXiv:2107.01592v1 fatcat:o5b6pn4x5jgyth2mu7ksktwyu4

Integrating Web-based and Corpus-based Techniques for Question Answering

Boris Katz, Jimmy J. Lin, Daniel Loreto, Wesley Hildebrandt, Matthew W. Bilotti, Sue Felshin, Aaron Fernandes, Gregory Marton, Federico Mora
2003 Text Retrieval Conference  
Database Lookup The use of surface patterns for answer extraction has proven to be an effective strategy for question answering.  ...  An often effective way to boost document retrieval recall is to employ query expansion techniques.  ... 
dblp:conf/trec/KatzLLHBFFMM03 fatcat:esordrwcsraqfezd4ydtenzxwq
« Previous Showing results 1 — 15 out of 42,654 results