Filters








147,916 Hits in 6.4 sec

Open Domain Question Answering Using Web Tables [article]

Kaushik Chakrabarti, Zhimin Chen, Siamak Shakeri, Guihong Cao
2020 arXiv   pre-print
However, many queries answerable using tables are non-factoid in nature. In this paper, we develop an open-domain QA approach using web tables that works for both factoid and non-factoid queries.  ...  Previous works on question answering (QA) using web tables have focused on factoid queries, i.e., those answerable with a short string like person name or a number.  ...  answering using web tables: Our work is most related to previous works on question answering using web tables [16, 21] .  ... 
arXiv:2001.03272v1 fatcat:2fkmnmcdvvggnazlhe4x4zxqke

A comparative study of web based and IR based question answering systems

Rosy Madaan, Sharma A.K, Ashutosh Dixit, Deepti Kapri, Renu Mudgal
2012 International Journal of Advances in Computing and Information Technology  
Search engine Question classification Answer extraction Answer selection WEB answer question user question Table 3 : 3 IR techniques used in IR based QA systems This table shows that  ...  Table 2.1 provides a comparison of example systems on the basis of data source used by them, their domain & their Web accessibility.  ... 
doi:10.6088/ijacit.12.10024 fatcat:vuapgnfov5es3fsu2bwl4n6zlu

Question Answering System, Approaches and Techniques: A Review

Ajitkumar M., Khillare S.A., C. Namrata
2016 International Journal of Computer Applications  
Question answering is a specialized area in the field of information retrieval Text Processing.  ...  Question Answering system has many application based on source of answering like extracting information from document, language learning, online examination etc.  ...  There are two types of question answering system i.e. open domain and closed domain.  ... 
doi:10.5120/ijca2016909587 fatcat:ru2papuclfcbdpyjzxnioptqu4

CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training [article]

Patrick Huber, Armen Aghajanyan, Barlas Oğuz, Dmytro Okhonko, Wen-tau Yih, Sonal Gupta, Xilun Chen
2022 arXiv   pre-print
With the rise of large-scale pre-trained language models, open-domain question-answering (ODQA) has become an important research topic in NLP.  ...  Based on the popular pre-training fine-tuning approach, we posit that an additional in-domain pre-training stage using a large-scale, natural, and diverse question-answering (QA) dataset can be beneficial  ...  Similar to in-domain pre-training, multiple domain-dependent pre-training tasks have been proposed for open-domain question-answering.  ... 
arXiv:2110.07731v2 fatcat:a7iutxmskzhy3hnsk74g7zu5rm

Introduction to the Special Issue on Question Answering

David Gunning, Vinay K. Chaudhri, Chris Welty
2010 The AI Magazine  
Included are articles on Project, the Semantic Research, Watson, True Knowledge, and TextRunner (University of Washington's clever use of statistical NL techniques to answer questions across the open web  ...  This special issue issue of AI Magazine presents six articles on some of the most interesting question answering systems in development today.  ...  simpler representation but cover the completely open domain of the web.  ... 
doi:10.1609/aimag.v31i3.2300 fatcat:ytotrlhuvnbynitvsih5np3p6a

A Comparative Evaluation of QA Systems over List Questions [chapter]

Patricia Nunes Gonçalves, António Horta Branco
2016 Lecture Notes in Computer Science  
The evaluation of a Question Answering system is a challenging task. In this paper we evaluate our system, LX-ListQuestion, a Web-based QA System that focuses on answering list questions.  ...  that indicate the usefulness of the system to the user by counting the number of questions for which the system provides at least one correct answer.  ...  The goal of an Open-domain QA system is to answer questions on any kind of subject domain [10] .  ... 
doi:10.1007/978-3-319-41552-9_11 fatcat:qfb3tmcrlzfjxhahnitko6hwdq

What Kind of Answers in Web Open Knowledge Resources: for Quiz Questions in Education

Hyo-Jung Oh, Yong Kim
2015 International Journal of u- and e- Service, Science and Technology  
To evaluate the usage of web open knowledge resources for QA in terms of educational purpose, we choose 'quiz' game as the target domain of television show.  ...  Automatic Question Answering (QA) system aims an appropriate answer for a natural language question. There are several attempts to apply QA techniques to education field in terms of tutoring system.  ...  It means our web open resources are enough to contain potential answers for quiz questions.  ... 
doi:10.14257/ijunesst.2015.8.9.26 fatcat:wu456zpokzamjmjl2we5bejodm

An Open-Domain QA System for e-Governance [article]

Radu Ion, Andrei-Marius Avram, Vasile Păiş, Maria Mitrofan, Verginica Barbu Mititelu, Elena Irimia, Valentin Badea
2022 arXiv   pre-print
The paper presents an open-domain Question Answering system for Romanian, answering COVID-19 related questions.  ...  The QA system pipeline involves automatic question processing, automatic query generation, web searching for the top 10 most relevant documents and answer extraction using a fine-tuned BERT model for Extractive  ...  Related work Open-domain QA (ODQA) aims at answering questions from large open-domain corpora (e.g., Wikipedia).  ... 
arXiv:2206.08046v1 fatcat:2szoeqbp2zdrfgb2syl233gtpa

Open- vs. Restricted-Domain QA Systems in the Biomedical Field

María-Dolores Olvera-Lobo, Juncal Gutiérrez-Artacho
2011 Journal of information science  
Keywords biomedical information; evaluation; open-domain question answering systems; question answering systems; restricted-domain question answering systems Journal of Information Science 37(2) 152-162  ...  To this end we analysed the performance of two open-domain and two restricted-domain QA systems. The research entailed a collection of 150 definitional questions from WebMed.  ...  It can find several examples of both types of QA systems available on the web, i.e. open-domain QA system TextMap Question Answer (http://brahms.isi. edu:8080/textmap/) and a restricted-domain QA systems  ... 
doi:10.1177/0165551511398575 fatcat:7au34kspejhl3pr3n2vqmyxvwu

An Embodied Conversational Agent for Intelligent Web Interaction on Pandemic Crisis Communication

Ong Goh, Chun Fung, Kok Wong, Arnold Depickere
2006 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology Workshops  
In this paper, we compare the interaction of AINI against two popular search engines, two question answering systems and two conversational systems.  ...  Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 02:03 from IEEE Xplore. Restrictions apply.  ...  Table 2 : 2 Responses from the question answering engines QUESTION ANSWERING ENGINES ENGINE RESPONSES AskJeeves Reply 4.183 million pages.  ... 
doi:10.1109/wi-iatw.2006.37 dblp:conf/iat/GohFWD06 fatcat:52eb5vsmlnewzn5lxae6an3s44

Question Answering over Curated and Open Web Sources [article]

Rishiraj Saha Roy, Avishek Anand
2020 arXiv   pre-print
The last few years have seen an explosion of research on the topic of automated question answering (QA), spanning the communities of information retrieval, natural language processing, and artificial intelligence  ...  This tutorial would cover the highlights of this really active period of growth for QA to give the audience a grasp over the families of algorithms that are currently being used.  ...  In this tutorial, we refer to knowledge graphs and Web tables as the curated Web, and all unstructured text available online as the open Web.  ... 
arXiv:2004.11980v3 fatcat:bavyc2xlrbazrphxhhgzzeitrq

Research on Open Domain Question Answering System [chapter]

Zhonglin Ye, Zheng Jia, Yan Yang, Junfu Huang, Hongfeng Yin
2015 Lecture Notes in Computer Science  
Aiming at open domain question answering system evaluation task in the fourth CCF Natural Language Processing and Chinese Computing Conference (NLPCC2015), a solution of automatic question answering which  ...  Firstly, SPE (Subject Predicate Extraction) algorithm is presented to find answers from the knowledge base, and then WKE (Web Knowledge Extraction) algorithm is used to extract answers from search engine  ...  This paper presents a solution of open domain question answering (QA).  ... 
doi:10.1007/978-3-319-25207-0_49 fatcat:rlwmo5j35neb7loosldx6w76ay

Open-Domain Question Answering Goes Conversational via Question Rewriting [article]

Raviteja Anantha, Svitlana Vakulenko, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi
2021 arXiv   pre-print
Answers to questions in the same conversation may be distributed across several web pages.  ...  We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA.  ...  Consequently, there is a clear need to extend open-domain question answering (QA) to a conversational setting.  ... 
arXiv:2010.04898v3 fatcat:r357s67rcrcjjkb7efe3cji3mu

Answering Complex Questions Using Open Information Extraction

Tushar Khot, Ashish Sabharwal, Peter Clark
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Open Information Extraction (Open IE) provides a way to generate semi-structured knowledge for QA, but to date such knowledge has only been used to answer simple questions with retrievalbased methods.  ...  While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques  ...  Acknowledgments The authors would like to thank Oren Etzioni for valuable feedback on an early draft of this paper, and Colin Arenz and Michal Guerquin for helping us develop this system.  ... 
doi:10.18653/v1/p17-2049 dblp:conf/acl/KhotSC17 fatcat:pa7o4kqbmjgwpke5r6reu7lgy4

Convolutional Neural Network: Text Classification Model for Open Domain Question Answering System [article]

Muhammad Zain Amin, Noman Nadeem
2019 arXiv   pre-print
We further propose a method to integrate Convolutional Neural Network Classifier to an open domain question answering system.  ...  Recently machine learning is being applied to almost every data domain one of which is Question Answering Systems (QAS).  ...  which makes it an open domain platform for question answering system.  ... 
arXiv:1809.02479v2 fatcat:uvhmz27tlfcljkvytjvks55x5i
« Previous Showing results 1 — 15 out of 147,916 results