Difference between revisions of "Reading Wikipedia to Answer Open-Domain Questions"

From Wikipedia Quality
Jump to: navigation, search
(+ infobox)
(Embed)
 
Line 11: Line 11:
 
== Overview ==
 
== Overview ==
 
This paper proposes to tackle open- domain [[question answering]] using [[Wikipedia]] as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Authors approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Authors experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.
 
This paper proposes to tackle open- domain [[question answering]] using [[Wikipedia]] as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Authors approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Authors experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.
 +
 +
== Embed ==
 +
=== Wikipedia Quality ===
 +
<code>
 +
<nowiki>
 +
Chen, Danqi; Fisch, Adam; Weston, Jason; Bordes, Antoine. (2017). "[[Reading Wikipedia to Answer Open-Domain Questions]]".DOI: 10.18653/v1/P17-1171.
 +
</nowiki>
 +
</code>
 +
 +
=== English Wikipedia ===
 +
<code>
 +
<nowiki>
 +
{{cite journal |last1=Chen |first1=Danqi |last2=Fisch |first2=Adam |last3=Weston |first3=Jason |last4=Bordes |first4=Antoine |title=Reading Wikipedia to Answer Open-Domain Questions |date=2017 |doi=10.18653/v1/P17-1171 |url=https://wikipediaquality.com/wiki/Reading_Wikipedia_to_Answer_Open-Domain_Questions}}
 +
</nowiki>
 +
</code>
 +
 +
=== HTML ===
 +
<code>
 +
<nowiki>
 +
Chen, Danqi; Fisch, Adam; Weston, Jason; Bordes, Antoine. (2017). &amp;quot;<a href="https://wikipediaquality.com/wiki/Reading_Wikipedia_to_Answer_Open-Domain_Questions">Reading Wikipedia to Answer Open-Domain Questions</a>&amp;quot;.DOI: 10.18653/v1/P17-1171.
 +
</nowiki>
 +
</code>

Latest revision as of 10:21, 12 August 2019


Reading Wikipedia to Answer Open-Domain Questions
Authors
Danqi Chen
Adam Fisch
Jason Weston
Antoine Bordes
Publication date
2017
DOI
10.18653/v1/P17-1171
Links
Original Preprint

Reading Wikipedia to Answer Open-Domain Questions - scientific work related to Wikipedia quality published in 2017, written by Danqi Chen, Adam Fisch, Jason Weston and Antoine Bordes.

Overview

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Authors approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Authors experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

Embed

Wikipedia Quality

Chen, Danqi; Fisch, Adam; Weston, Jason; Bordes, Antoine. (2017). "[[Reading Wikipedia to Answer Open-Domain Questions]]".DOI: 10.18653/v1/P17-1171.

English Wikipedia

{{cite journal |last1=Chen |first1=Danqi |last2=Fisch |first2=Adam |last3=Weston |first3=Jason |last4=Bordes |first4=Antoine |title=Reading Wikipedia to Answer Open-Domain Questions |date=2017 |doi=10.18653/v1/P17-1171 |url=https://wikipediaquality.com/wiki/Reading_Wikipedia_to_Answer_Open-Domain_Questions}}

HTML

Chen, Danqi; Fisch, Adam; Weston, Jason; Bordes, Antoine. (2017). &quot;<a href="https://wikipediaquality.com/wiki/Reading_Wikipedia_to_Answer_Open-Domain_Questions">Reading Wikipedia to Answer Open-Domain Questions</a>&quot;.DOI: 10.18653/v1/P17-1171.