Computational Approaches to Sentence Completion
Geoffrey Zweig, John C. Platt, Christopher Meek, Christopher J. C. Burges, Ainur Yessenalina, Qiang Liu · 2012
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. 1