Paper: Computational Approaches to Sentence Completion

ACL ID P12-1063
Title Computational Approaches to Sentence Completion
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

This paper studies the problem of sentence- level semantic coherence by answering SAT- style sentence completion questions. These questions test the ability of algorithms to dis- tinguish sense from nonsense based on a vari- ety 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 comple- tion 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...