NLP systems, in order to be robust, must handle novel and ill-formed input. One common type of error involves the use of non-standard prepositions to mark arguments. In this paper, we argue that such errors can be handled in a systematic fashion, and that a system designed to handle them offers

In the literature on prepositions, a distinction between “lexical ” and “functional ” uses is com-monly assumed. In most theoretical accounts, this contrast is treated as a binary classification, and every preposition is assigned one of two distinct representations, depending on its lexical

assumptions now standard within the Government-Binding (GB) framework. The central empirical problem addressed is the question of the proper analysis of the so-called \Poss-ing " gerund in English. This construction possesses simultaneously many properties of sentences, and many properties of noun

as multinomial distributions over a discrete vocabulary, and the HMM parameters are set to maximize the likelihood of the observations. This paper presents a new Markovian sequence model, closely related to HMMs, that allows observations to be represented as arbitrary overlapping features (such as word

-backed coup deposed the reformist government of Col. Jacobo Arbenz Guzmán in 1954. Moderates of the political center. embattled but alive in E1 Salvador, have virtually disappeared in Guatemala-joining more than 30.000 victims of terror over the last tifteen vears. “The situation in Guatemala is much more

Abstract not found

WordNet is an on-line lexical reference system whose design is inspired by current

Abstract not found

The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last ten years, due to the increased availability of documents in digital form and the ensuing need to organize them. In the research community the dominant approach to this problem is based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristics of the categories. The advantages of this approach over the knowledge engineering approach (consisting in the manual definition of a classifier by domain experts) are a very good effectiveness, considerable savings in terms of expert labor power, and straightforward portability to different domains. This survey discusses the main approaches to text categorization that fall within the machine learning paradigm. We will discuss in detail issues pertaining to three different problems, namely document representation, classifier construction, and classifier evaluation.

This paper proposes a new theory of the relationship between the sentence processing mechanism and the available computational resources. This theory -- the Syntactic Prediction Locality Theory (SPLT) -- has two components: an integration cost component and a component for the memory cost associated with keeping track of obligatory syntactic requirements. Memory cost is