Difference between revisions of "Evaluating a Statistical Ccg Parser on Wikipedia"

From Wikipedia Quality
Jump to: navigation, search
(Adding embed)
(Adding categories)
 
Line 32: Line 32:
 
</nowiki>
 
</nowiki>
 
</code>
 
</code>
 +
 +
 +
 +
[[Category:Scientific works]]

Latest revision as of 00:41, 9 March 2021


Evaluating a Statistical Ccg Parser on Wikipedia
Authors
Matthew Honnibal
Joel Nothman
James R. Curran
Publication date
2009
DOI
10.3115/1699765.1699771
Links
Original

Evaluating a Statistical Ccg Parser on Wikipedia - scientific work related to Wikipedia quality published in 2009, written by Matthew Honnibal, Joel Nothman and James R. Curran.

Overview

The vast majority of parser evaluation is conducted on the 1984 Wall Street Journal (WSJ). In-domain evaluation of this kind is important for system development, but gives little indication about how the parser will perform on many practical problems. Wikipedia is an interesting domain for parsing that has so far been under-explored. Authors present statistical parsing results that for the first time provide information about what sort of performance a user parsing Wikipedia text can expect.

Embed

Wikipedia Quality

Honnibal, Matthew; Nothman, Joel; Curran, James R.. (2009). "[[Evaluating a Statistical Ccg Parser on Wikipedia]]". Association for Computational Linguistics. DOI: 10.3115/1699765.1699771.

English Wikipedia

{{cite journal |last1=Honnibal |first1=Matthew |last2=Nothman |first2=Joel |last3=Curran |first3=James R. |title=Evaluating a Statistical Ccg Parser on Wikipedia |date=2009 |doi=10.3115/1699765.1699771 |url=https://wikipediaquality.com/wiki/Evaluating_a_Statistical_Ccg_Parser_on_Wikipedia |journal=Association for Computational Linguistics}}

HTML

Honnibal, Matthew; Nothman, Joel; Curran, James R.. (2009). &quot;<a href="https://wikipediaquality.com/wiki/Evaluating_a_Statistical_Ccg_Parser_on_Wikipedia">Evaluating a Statistical Ccg Parser on Wikipedia</a>&quot;. Association for Computational Linguistics. DOI: 10.3115/1699765.1699771.