In previous research in automatic verb classification, syntactic features have proved the most useful features, although manual classifications rely heavily on semantic features. We show, in contrast with previous work, that considerable additional improvement can be obtained by using semantic features in automatic classification: verb selectional preferences acquired from corpus data using a fully unsupervised method. We report these promising results using a new framework for verb clustering which incorporates a recent subcategorization acquisition system, rich syntactic-semantic feature sets, and a variation of spectral clustering which performs particularly well in high dimensional feature space. 1

This paper describes the application of so-called topic models to selectional preference induction. Three models related to Latent Dirichlet Allocation, a proven method for modelling document-word cooccurrences, are presented and evaluated on datasets of human plausibility judgements. Compared to previously proposed techniques, these models perform very competitively, especially for infrequent predicate-argument combinations where they exceed the quality of Web-scale predictions while using relatively little data. 1

The appropriateness of paraphrases for words depends often on context: “grab ” can replace “catch” in “catch a ball”, but not in “catch a cold”. Structured Vector Space (SVS) (Erk and Padó, 2008) is a model that computes word meaning in context in order to assess the appropriateness of such paraphrases. This paper investigates “best-practice ” parameter settings for SVS, and it presents a method to obtain large datasets for paraphrase assessment from corpora with WSD annotation. 1

We present a novel approach to automatic metaphor identification in unrestricted text. Starting from a small seed set of manually annotated metaphorical expressions, the system is capable of harvesting a large number of metaphors of similar syntactic structure from a corpus. Our method is distinguished from previous work in that it does not employ any hand-crafted knowledge, other than the initial seed set, but, in contrast, captures metaphoricity by means of verb and noun clustering. Being the first to employ unsupervised methods for metaphor identification, our system operates with the precision of 0.79. 1

Abstract. Verb classifications have been used to support a number of practical tasks and applications, such as parsing, information extraction, question-answering, and machine translation. However, large-scale exploitation of verb classes in real-world or domain-sensitive tasks has not been possible because existing manually built classifications are incomprehensive. This paper describes recent and on-going research on extending and acquiring lexical classifications automatically. The automatic approach is attractive since it is cost-effective and opens up the opportunity of learning and tuning lexical classifications for the application and domain in question. However, the development of an optimal approach is challenging, and requires not only expertise in machine learning but also a good understanding of the linguistic principles of lexical classification.

Abstract not found

In this paper, we present a novel approach which incorporates the web-derived selectional preferences to improve statistical dependency parsing. Conventional selectional preference learning methods have usually focused on word-to-class relations, e.g., a verb selects as its subject a given nominal class. This paper extends previous work to wordto-word selectional preferences by using webscale data. Experiments show that web-scale data improves statistical dependency parsing, particularly for long dependency relationships. There is no data like more data, performance improves log-linearly with the number of parameters (unique N-grams). More importantly, when operating on new domains, we show that using web-derived selectional preferences is essential for achieving robust performance. 1

This paper addresses context matching in textual inference. We formulate the task under the Contextual Preferences framework which broadly captures contextual aspects of inference. We propose a generic classificationbased scheme under this framework which coherently attends to context matching in inference and may be employed in any inferencebased task. As a test bed for our scheme we use the Name-based Text Categorization (TC) task. We define an integration of Contextual Preferences into the TC setting and present a concrete self-supervised model which instantiates the generic scheme and is applied to address context matching in the TC task. Experiments on standard TC datasets show that our approach outperforms the state of the art in context modeling for Name-based TC. 1

Most NLP systems make predictions based solely on linguistic (textual or spoken) input. We show how to use visual information to make better linguistic predictions. We focus on selectional preference; specifically, determining the plausible noun arguments for particular verb predicates. For each argument noun, we extract visual features from corresponding images on the web. For each verb predicate, we train a classifier to select the visual features that are indicative of its preferred arguments. We show that for certain verbs, using visual information can significantly improve performance over a baseline. For the successful cases, visual information is useful even in the presence of cooccurrence information derived from webscale text. We assess a variety of training configurations, which vary over classes of visual features, methods of image acquisition, and numbers of images. 1

Metaphor is highly frequent in language, which makes its computational processing indispensable for real-world NLP applications addressing semantic tasks. Previous approaches to metaphor modelling rely on task-specific hand-coded knowledge and operate on a limited domain or a subset of phenomena. We present the first integrated open-domain statistical model of metaphor processing in unrestricted text. Our method first identifies metaphorical expressions in running text and then paraphrases them with their literal paraphrases. Such a text-to-text model of metaphor interpretation is compatible with other NLP applications that can benefit from metaphor resolution. Our approach is minimally supervised, it relies on the state-of-the-art parsing and lexical acquisition technologies (distributional clustering and selectional preference induction) and operates with a high accuracy. 1.