Unsupervised Prediction of Acceptability Judgements
Jey Han Lau, Alexander Clark, Shalom Lappin, C Zong (ed.), M Strube (ed.)
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) | ASSOC COMPUTATIONAL LINGUISTICS-ACL | Published : 2015
In this paper we present the task of unsupervised prediction of speakers' acceptability judgements. We use a test set generated from the British National Corpus (BNC) containing both grammatical sentences and sentences containing a variety of syntactic infelicities introduced by round trip machine translation. This set was annotated for acceptability judgements through crowd sourcing. We trained a variety of unsupervised language models on the original BNC, and tested them to see the extent to which they could predict mean speakers' judgements on the test set. To map probability to acceptability, we experimented with several normalisation functions to neutralise the effects of sentence lengt..View full abstract
Awarded by Economic and Social Research Council of the UK
The research reported here was done as part of the Statisticsal Models of Grammar (SMOG) project at King's College London(www.dcs.kcl.ac.uk/staf f/lappin/smog/), funded by grant ES/J022969/1 from the Economic and Social Research Council of the UK.