Difference between revisions of "Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts"
(Creating a new page - Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts) |
(+ cat.) |
||
(3 intermediate revisions by 3 users not shown) | |||
Line 1: | Line 1: | ||
− | '''Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts''' - scientific work related to Wikipedia quality published in 2007, written by Suzan Verberne. | + | {{Infobox work |
+ | | title = Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts | ||
+ | | date = 2007 | ||
+ | | authors = [[Suzan Verberne]] | ||
+ | | link = http://repository.ubn.ru.nl/handle/2066/44141 | ||
+ | }} | ||
+ | '''Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts''' - scientific work related to [[Wikipedia quality]] published in 2007, written by [[Suzan Verberne]]. | ||
== Overview == | == Overview == | ||
− | In this paper the research focus is on the task of answer extraction for why-questions. As opposed to techniques for factoid QA, flnding answers to why- questions involves exploiting text structure. Therefore, authors approach the answer extraction problem as a discourse analysis task, using Rhetorical Structure Theory (RST) as framework. Authors evaluated this method using a set of why-questions that have been asked to the online question answering system answers.com with a corpus of answer fragments from Wikipedia, manually annotated with RST structures. The maximum recall that can be obtained by answer extraction procedure is about 60%. Authors suggest paragraph retrieval as supplementary and alternative approach to RST-based answer extraction. | + | In this paper the research focus is on the task of answer extraction for why-questions. As opposed to techniques for factoid QA, flnding answers to why- questions involves exploiting text structure. Therefore, authors approach the answer extraction problem as a discourse analysis task, using Rhetorical Structure Theory (RST) as framework. Authors evaluated this method using a set of why-questions that have been asked to the online [[question answering]] system answers.com with a corpus of answer fragments from [[Wikipedia]], manually annotated with RST structures. The maximum recall that can be obtained by answer extraction procedure is about 60%. Authors suggest paragraph retrieval as supplementary and alternative approach to RST-based answer extraction. |
+ | |||
+ | == Embed == | ||
+ | === Wikipedia Quality === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | Verberne, Suzan. (2007). "[[Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts]]". Dublin : Trinity College. | ||
+ | </nowiki> | ||
+ | </code> | ||
+ | |||
+ | === English Wikipedia === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | {{cite journal |last1=Verberne |first1=Suzan |title=Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts |date=2007 |url=https://wikipediaquality.com/wiki/Evaluating_Answer_Extraction_for_Why-Qa_Using_Rst-Annotated_Wikipedia_Texts |journal=Dublin : Trinity College}} | ||
+ | </nowiki> | ||
+ | </code> | ||
+ | |||
+ | === HTML === | ||
+ | <code> | ||
+ | <nowiki> | ||
+ | Verberne, Suzan. (2007). &quot;<a href="https://wikipediaquality.com/wiki/Evaluating_Answer_Extraction_for_Why-Qa_Using_Rst-Annotated_Wikipedia_Texts">Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts</a>&quot;. Dublin : Trinity College. | ||
+ | </nowiki> | ||
+ | </code> | ||
+ | |||
+ | |||
+ | |||
+ | [[Category:Scientific works]] |
Latest revision as of 08:34, 9 June 2020
Authors | Suzan Verberne |
---|---|
Publication date | 2007 |
Links | Original |
Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts - scientific work related to Wikipedia quality published in 2007, written by Suzan Verberne.
Overview
In this paper the research focus is on the task of answer extraction for why-questions. As opposed to techniques for factoid QA, flnding answers to why- questions involves exploiting text structure. Therefore, authors approach the answer extraction problem as a discourse analysis task, using Rhetorical Structure Theory (RST) as framework. Authors evaluated this method using a set of why-questions that have been asked to the online question answering system answers.com with a corpus of answer fragments from Wikipedia, manually annotated with RST structures. The maximum recall that can be obtained by answer extraction procedure is about 60%. Authors suggest paragraph retrieval as supplementary and alternative approach to RST-based answer extraction.
Embed
Wikipedia Quality
Verberne, Suzan. (2007). "[[Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts]]". Dublin : Trinity College.
English Wikipedia
{{cite journal |last1=Verberne |first1=Suzan |title=Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts |date=2007 |url=https://wikipediaquality.com/wiki/Evaluating_Answer_Extraction_for_Why-Qa_Using_Rst-Annotated_Wikipedia_Texts |journal=Dublin : Trinity College}}
HTML
Verberne, Suzan. (2007). "<a href="https://wikipediaquality.com/wiki/Evaluating_Answer_Extraction_for_Why-Qa_Using_Rst-Annotated_Wikipedia_Texts">Evaluating Answer Extraction for Why-Qa Using Rst-Annotated Wikipedia Texts</a>". Dublin : Trinity College.