Sciweavers

Share
ACL
2012

Computational Approaches to Sentence Completion

7 years 5 months ago
Computational Approaches to Sentence Completion
This paper studies the problem of sentencelevel semantic coherence by answering SATstyle sentence completion questions. These questions test the ability of algorithms to distinguish sense from nonsense based on a variety of sentence-level phenomena. We tackle the problem with two approaches: methods that use local lexical information, such as the n-grams of a classical language model; and methods that evaluate global coherence, such as latent semantic analysis. We evaluate these methods on a suite of practice SAT questions, and on a recently released sentence completion task based on data taken from five Conan Doyle novels. We find that by fusing local and global information, we can exceed 50% on this task (chance baseline is 20%), and we suggest some avenues for further research.
Geoffrey Zweig, John C. Platt, Christopher Meek, C
Added 29 Sep 2012
Updated 29 Sep 2012
Type Journal
Year 2012
Where ACL
Authors Geoffrey Zweig, John C. Platt, Christopher Meek, Christopher J. C. Burges, Ainur Yessenalina, Qiang Liu
Comments (0)
books