9,781 Hits in 5.5 sec

Semantic passage segmentation based on sentence topics for question answering

Hyo-Jung Oh, Sung Hyon Myaeng, Myung-Gil Jang
2007 Information Sciences  
We propose a semantic passage segmentation method for a Question Answering (QA) system.  ...  We ran experiments to evaluate the proposed method and its impact on application tasks, passage retrieval and template-filling for question answering.  ...  Conclusion We proposed a semantic passage segmentation method based on the notion of sentence topics to enhance the performance of our question answer system.  ... 
doi:10.1016/j.ins.2007.02.038 fatcat:3j6o2hodovd77j44lquqkdtevi

Using Syntactic and Semantic Relation Analysis in Question Answering

Renxu Sun, Jing Jiang, Yee Fan Tan, Hang Cui, Tat-Seng Chua, Min-Yen Kan
2005 Text Retrieval Conference  
Finally, we use the semantic similarity scores to rank passages. For a question, we first use a density based passage retrieval method to retrieve the top 100 passages.  ...  We than rank these 100 passages based on their semantic similarities to the question, as defined above. 4.3 Answer Projection and Verification After we obtain the answer nuggets from the web, we need  ... 
dblp:conf/trec/SunJTCCK05 fatcat:ksuzci6uezfqpff4veyikjamfe

A Hybrid Question Answering System

Waheeb Ahmed, P. Babu Anto
2019 Current Journal of Applied Science and Technology  
In this study, we propose a hybrid Question Answering (QA) system for Arabic language. The system combines textual and structured knowledge-Base (KB) data for question answering.  ...  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.  ...  In question classification, it analyzes the question semantically and identifies the answer type (Table 1 ) where the answer type is a label generated based on the semantic classification of the question  ... 
doi:10.9734/cjast/2019/v34i330129 fatcat:g3hnnq6syffirezy2frulsph6y

Query Focused Multi-Document Summarization with Distant Supervision [article]

Yumo Xu, Mirella Lapata
2020 arXiv   pre-print
Due to the lack of training data, existing work relies heavily on retrieval-style methods for estimating the relevance between queries and text segments.  ...  Under this framework, a trained evidence estimator further discerns which retrieved segments might answer the query for final selection in the summary.  ...  ., a user might be looking for an overview summary or a more detailed one which would allow them to answer a specific question).  ... 
arXiv:2004.03027v1 fatcat:m473vytlvfhz5op5gr6f7r44iq

Question Answering for Machine Reading with Lexical Chain

Ling Cao, Xipeng Qiu, Xuanjing Huang
2011 Conference and Labs of the Evaluation Forum  
Question answering for machine reading (QA4MR) is a task to understand the meaning communicated by a text. In this paper, we present our system in QA4MRE 1 .  ...  On the QA4MRE test dataset, our system achieves the c@1 measure of 0.28 and 0.26 for the two submissions, respectively.  ...  In our system, text (including passage, question and choices) is sent to preprocessing module initially. (1) Sentence segmentation for each passage. (2) Tokenization for each sentence, question and choice  ... 
dblp:conf/clef/CaoQH11 fatcat:bropypqqfrc3jcozym74vvvnlq

Use of Metadata for Question Answering and Novelty Tasks

Kenneth C. Litkowski
2003 Text Retrieval Conference  
CL Research's question-answering system for TREC 2003 was modified away from reliance on database technology to the core underlying technology of using massive XML-tagging for processing both questions  ...  We have implemented further routines since our official submission, improving our scores to 0.18 and 0.23 for the exact answer and passages tasks, respectively.  ...  For prepositions, the attributes include its segment, the type of semantic relation it instantiates (based on disambiguation of the preposition) and its arguments (both the prepositional object and the  ... 
dblp:conf/trec/Litkowski03 fatcat:zh26q22hqbbllg7widh3n6rfki

Entity-Based Relevance Feedback for Genomic List Answer Retrieval

Nicola Stokes, Yi Li, Lawrence Cavedon, Eric Huang, Jiawen Rong, Justin Zobel
2007 Text Retrieval Conference  
For the 2007 Genomic task, we also modified this system architecture with an additional dynamic form of query expansion called entity-based relevance feedback.  ...  Our final modification to the system, aims to maximizing the passage-level MAP score, by dropping sentences that do not contain any query concepts, from the beginning and the end of a candidate paragraph  ...  The 2007 Genomics Track focused on retrieving passages that respond to questions requiring list-type answers.  ... 
dblp:conf/trec/StokesLCHRZ07 fatcat:p3snwyz24vfkdibi5tawpzcsfi

Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension

Zhengyuan Liu, Nancy Chen
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Unlike passages, where sentences are often the default semantic modeling unit, in multi-turn conversations, a turn is a topically coherent unit embodied with immediately relevant context, making it a linguistically  ...  intuitive segment for computationally modeling verbal interactions.  ...  Tong at Changi General Hospital for insightful discussions. We also thank the anonymous reviewers for their precious feedback to help improve and extend this piece of work.  ... 
doi:10.18653/v1/p19-1543 dblp:conf/acl/LiuC19 fatcat:pg3gcec4oje2rnucwrsyagb5mm

SiteQ/J: A Question Answering System for Japanese

Seungwoo Lee, Gary Geunbae Lee
2002 NTCIR Conference on Evaluation of Information Access Technologies  
Through analyzing the previous TREC QA data, we defined passage and developed passage selection method suitable for Question Answering.  ...  Using Lexico-Semantic Patterns (LSP), we identify answer type of a question and detect answer candidates without any deep linguistic analysis of the texts.  ...  Many QA systems defined their own passage (sentence, paragraph, topical segment, etc) and developed various ranking measures.  ... 
dblp:conf/ntcir/LeeL02 fatcat:n5w6eqnh3zbxral7yf2y6542aa

WHU Question Answering System at NTCIR-8 ACLIA Task

Han Ren, Donghong Ji, Jing Wan
2010 NTCIR Conference on Evaluation of Information Access Technologies  
With regard to the question answering system, a PLSA based approach is introduced for answer sentence acquisition.  ...  For answer ranking, our system expands the question set by summarizing relevant sentences from a web knowledge base and leverages both semantic and statistical information of questions.  ...  These passages may not be considered in passage retrieval in most cases or their ranks are very low, whereas some of them are potentially relevant to the questions. 2) our PLSA based answer sentence acquisition  ... 
dblp:conf/ntcir/RenJW10 fatcat:gx66fm4oyfdind6qvx2q3hiroy

An annotation similarity model in passage ranking for historical fact validation

Jun Araki, Jamie Callan
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
State-of-the-art question answering (QA) systems employ passage retrieval based on bag-of-words similarity models with respect to a query and a passage.  ...  Historical fact validation is a subtask to determine whether a given sentence tells us historically correct information, which is important for a QA task on world history.  ...  We use Stanford CoreNLP 6 for sentence segmentation. We also restrict the number of retrieved passages to Np for subsequent processes.  ... 
doi:10.1145/2600428.2609522 dblp:conf/sigir/ArakiC14 fatcat:7m74ssquxvbq7p7ux33aeh3zpm

Comparing segmentation strategies for efficient video passage retrieval

Christian Wartena
2012 2012 10th International Workshop on Content-Based Multimedia Indexing (CBMI)  
Passage retrieval has mainly been studied to improve document retrieval and to enable question answering.  ...  We compare the effect of different text segmentation strategies on speech based passage retrieval of video.  ...  Indirectly, passage retrieval is evaluated by its use for question answering and for improving document retrieval. Results in these domains suggest that the sliding window strategy performs best.  ... 
doi:10.1109/cbmi.2012.6269850 dblp:conf/cbmi/Wartena12 fatcat:dfhic3abpjhohnbk2wjkkqaaju

Harnessing Semantics for Answer Sentence Retrieval

Ruey-Cheng Chen, Damiano Spina, W. Bruce Croft, Mark Sanderson, Falk Scholer
2015 Proceedings of the Eighth Workshop on Exploiting Semantic Annotations in Information Retrieval - ESAIR '15  
Finding answer passages from the Web is a challenging task. One major difficulty is to retrieve sentences that may not have many terms in common with the question.  ...  In this paper, we experiment with two semantic approaches for finding non-factoid answers using a learning-to-rank retrieval setting.  ...  We focus on a relatively new and perhaps more difficult retrieval task called answer passage retrieval [7] , a specialized question answering task that looks for non-factoid, multiple-sentence answers  ... 
doi:10.1145/2810133.2810136 dblp:conf/cikm/ChenSCSS15 fatcat:ilnvoxagsva53csoigvkzgtw6a

ILQUA--An IE-Driven Question Answering System

Min Wu, Michelle Duan, Samira Shaikh, Sharon G. Small, Tomek Strzalkowski
2005 Text Retrieval Conference  
Acknowledgements Here the authors acknowledge thanks to Ting Liu, Xiaoyu Zheng and Zhenyu Dai for their efforts in the ILQUA development in 2003.  ...  The top 100 documents retrieved by Inquery are tagged and segmented into passages. These passages are filtered by answer target type, question terms and topic terms.  ...  For each topic, the answer nuggets and a list of sentences containing answer nuggets (created by Ken Litkowski) are provided on TREC website.  ... 
dblp:conf/trec/WuDSSS05 fatcat:royymvcc5vfbnf24lrlgwwljsi

ILQUA at TREC 2006

Min Wu, Tomek Strzalkowski
2006 Text Retrieval Conference  
To answer "Factoid" and "List" questions, we apply our answer extraction methods on NE-tagged passages or sentences.  ...  For each topic, the answer nuggets and a list of sentences containing answer nuggets (created by Ken Litkowski) are provided on TREC website.  ... 
dblp:conf/trec/WuS06 fatcat:tztrdwudcvfvthqohjrabl7sii
« Previous Showing results 1 — 15 out of 9,781 results