Passage retrieval in a question answering system.
Pyykkö, Juri ; Weegar, Rebecka and Nugues, Pierre LU
(2014)
The Fifth Swedish Language Technology Conference (SLTC 2014)
- Abstract
- In this paper, we describe a passage retrieval component for a questioning answering system and we evaluate its performance on
Swedish documents. We used a corpus of questions and answers transcribed from the Swedish board game Kvitt eller dubbelt
and, as source for the passages, we used the articles of the Swedish version of Wikipedia. We show that Wikipedia is a suitable
knowledge source to answer the game questions. For answers consisting of one word, we could extract passages of text that
contained the right answer for 91% of the questions and when these answers corresponded to an entity, we found and ranked
correct answers for up to 75% of the questions.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5115017
- author
- Pyykkö, Juri
; Weegar, Rebecka
and Nugues, Pierre
LU
- organization
- publishing date
- 2014
- type
- Contribution to conference
- publication status
- published
- subject
- conference name
- The Fifth Swedish Language Technology Conference (SLTC 2014)
- conference location
- Uppsala, Sweden
- conference dates
- 2014-11-13 - 2014-11-14
- language
- English
- LU publication?
- yes
- id
- 7cabb4e7-16cd-4e43-b421-75db3b1f91ba (old id 5115017)
- alternative location
- http://www2.lingfil.uu.se/SLTC2014/abstracts/sltc2014_submission_3.pdf
- date added to LUP
- 2016-04-04 13:25:56
- date last changed
- 2021-05-06 16:28:07
@misc{7cabb4e7-16cd-4e43-b421-75db3b1f91ba,
abstract = {{In this paper, we describe a passage retrieval component for a questioning answering system and we evaluate its performance on<br/><br>
Swedish documents. We used a corpus of questions and answers transcribed from the Swedish board game Kvitt eller dubbelt<br/><br>
and, as source for the passages, we used the articles of the Swedish version of Wikipedia. We show that Wikipedia is a suitable<br/><br>
knowledge source to answer the game questions. For answers consisting of one word, we could extract passages of text that<br/><br>
contained the right answer for 91% of the questions and when these answers corresponded to an entity, we found and ranked<br/><br>
correct answers for up to 75% of the questions.}},
author = {{Pyykkö, Juri and Weegar, Rebecka and Nugues, Pierre}},
language = {{eng}},
title = {{Passage retrieval in a question answering system.}},
url = {{http://www2.lingfil.uu.se/SLTC2014/abstracts/sltc2014_submission_3.pdf}},
year = {{2014}},
}