tailieunhanh - Báo cáo khoa học: "Modelling Semantic Role Plausibility in Human Sentence Processing"

We present the psycholinguistically motivated task of predicting human plausibility judgements for verb-role-argument triples and introduce a probabilistic model that solves it. We also evaluate our model on the related role-labelling task, and compare it with a standard role labeller. For both tasks, our model benefits from classbased smoothing, which allows it to make correct argument-specific predictions despite a severe sparse data problem. The standard labeller suffers from sparse data and a strong reliance on syntactic cues, especially in the prediction task. . | Modelling Semantic Role Plausibility in Human Sentence Processing Ulrike Padó and Matthew Crocker Computational Linguistics Saarland University 66041 Saarbrucken Germany ulrike crocker @ Frank Keller School of Informatics University of Edinburgh 2 Buccleuch Place Edinburgh EH8 9LW UK keller@ Abstract We present the psycholinguistically motivated task of predicting human plausibility judgements for verb-role-argument triples and introduce a probabilistic model that solves it. We also evaluate our model on the related role-labelling task and compare it with a standard role labeller. For both tasks our model benefits from classbased smoothing which allows it to make correct argument-specific predictions despite a severe sparse data problem. The standard labeller suffers from sparse data and a strong reliance on syntactic cues especially in the prediction task. 1 Introduction Computational psycholinguistics is concerned with modelling human language processing. Much work has gone into the exploration of sentence comprehension. Syntactic preferences that unfold during the course of the sentence have been successfully modelled using incremental probabilistic context-free parsing models . Jurafsky 1996 Crocker and Brants 2000 . These models assume that humans prefer the most likely structural alternative at each point in the sentence. If the preferred structure changes during processing such models correctly predict processing difficulty for a range of experimentally investigated constructions. They do not however incorporate an explicit notion of semantic processing while there are many phenomena in human sentence processing that demonstrate a non-trivial interaction of syntactic preferences and semantic plausibility. Consider for example the well-studied case of reduced relative clause constructions. When incrementally processing the sentence The deer shot by the hunter was used as a trophy there is a local ambiguity at shot between .