tailieunhanh - Báo cáo khoa học: "Exemplar-Based Models for Word Meaning In Context"

This paper describes ongoing work on distributional models for word meaning in context. We abandon the usual one-vectorper-word paradigm in favor of an exemplar model that activates only relevant occurrences. On a paraphrasing task, we find that a simple exemplar model outperforms more complex state-of-the-art models. | Exemplar-Based Models for Word Meaning In Context Katrin Erk Sebastian Pado Department of Linguistics Institut fur maschinelle Sprachverarbeitung University of Texas at Austin Stuttgart University pado@ Abstract This paper describes ongoing work on distributional models for word meaning in context. We abandon the usual one-vector-per-word paradigm in favor of an exemplar model that activates only relevant occurrences. On a paraphrasing task we find that a simple exemplar model outperforms more complex state-of-the-art models. 1 Introduction Distributional models are a popular framework for representing word meaning. They describe a lemma through a high-dimensional vector that records co-occurrence with context features over a large corpus. Distributional models have been used in many NLP analysis tasks Salton et al. 1975 McCarthy and Carroll 2003 Salton et al. 1975 as well as for cognitive modeling Baroni and Lenci 2009 Landauer and Dumais 1997 McDonald and Ramscar 2001 . Among their attractive properties are their simplicity and versatility as well as the fact that they can be acquired from corpora in an unsupervised manner. Distributional models are also attractive as a model of word meaning in context since they do not have to rely on fixed sets of dictionary sense with their well-known problems Kilgarriff 1997 McCarthy and Navigli 2009 . Also they can be used directly for testing paraphrase applicability Szpektor et al. 2008 a task that has recently become prominent in the context of textual entailment Bar-Haim et al. 2007 . However polysemy is a fundamental problem for distributional models. Typically distributional models compute a single type vector for a target word which contains cooccurrence counts for all the occurrences of the target in a large corpus. If the target is polysemous this vector mixes contextual features for all the senses of the target. For example among the top 20 features for coach we get .