Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites
D. Bernhard, and I. Gurevych. Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications, page 44--52. Stroudsburg, PA, USA, Association for Computational Linguistics, (2008)
Abstract
Information overload is a well-known problem which can be particularly detrimental to learners. In this paper, we propose a method to support learners in the information seeking process which consists in answering their questions by retrieving question paraphrases and their corresponding answers from social Q&A sites. Given the novelty of this kind of data, it is crucial to get a better understanding of how questions in social Q&A sites can be automatically analysed and retrieved. We discuss and evaluate several pre-processing strategies and question similarity metrics, using a new question paraphrase corpus collected from the WikiAnswers Q&A site. The results show that viable performance levels of more than 80% accuracy can be obtained for the task of question paraphrase retrieval.
Description
Answering learners' questions by retrieving question paraphrases from social Q&A sites
%0 Conference Paper
%1 Bernhard:2008:ALQ:1631836.1631842
%A Bernhard, Delphine
%A Gurevych, Iryna
%B Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications
%C Stroudsburg, PA, USA
%D 2008
%I Association for Computational Linguistics
%K Social-Search Social_Q&A social-information-access
%P 44--52
%T Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites
%U http://dl.acm.org/citation.cfm?id=1631836.1631842
%X Information overload is a well-known problem which can be particularly detrimental to learners. In this paper, we propose a method to support learners in the information seeking process which consists in answering their questions by retrieving question paraphrases and their corresponding answers from social Q&A sites. Given the novelty of this kind of data, it is crucial to get a better understanding of how questions in social Q&A sites can be automatically analysed and retrieved. We discuss and evaluate several pre-processing strategies and question similarity metrics, using a new question paraphrase corpus collected from the WikiAnswers Q&A site. The results show that viable performance levels of more than 80% accuracy can be obtained for the task of question paraphrase retrieval.
%@ 978-1-932432-08-4
@inproceedings{Bernhard:2008:ALQ:1631836.1631842,
abstract = {Information overload is a well-known problem which can be particularly detrimental to learners. In this paper, we propose a method to support learners in the information seeking process which consists in answering their questions by retrieving question paraphrases and their corresponding answers from social Q&A sites. Given the novelty of this kind of data, it is crucial to get a better understanding of how questions in social Q&A sites can be automatically analysed and retrieved. We discuss and evaluate several pre-processing strategies and question similarity metrics, using a new question paraphrase corpus collected from the WikiAnswers Q&A site. The results show that viable performance levels of more than 80% accuracy can be obtained for the task of question paraphrase retrieval.},
acmid = {1631842},
added-at = {2018-02-14T01:06:50.000+0100},
address = {Stroudsburg, PA, USA},
author = {Bernhard, Delphine and Gurevych, Iryna},
biburl = {https://www.bibsonomy.org/bibtex/2c6e7539140ac76b97045ec9b4ee7e429/aziz885},
booktitle = {Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications},
description = {Answering learners' questions by retrieving question paraphrases from social Q&A sites},
interhash = {0163615472aee6e3a8d4f46e07845f42},
intrahash = {c6e7539140ac76b97045ec9b4ee7e429},
isbn = {978-1-932432-08-4},
keywords = {Social-Search Social_Q&A social-information-access},
location = {Columbus, Ohio},
numpages = {9},
pages = {44--52},
publisher = {Association for Computational Linguistics},
series = {EANL '08},
timestamp = {2018-02-14T01:06:50.000+0100},
title = {Answering Learners’ Questions by Retrieving Question Paraphrases from Social Q&A Sites},
url = {http://dl.acm.org/citation.cfm?id=1631836.1631842},
year = 2008
}