Abstract not found

Fourteen linguistically-motivated numeri- cal indicators are evaluated for their abil- ity to categorize verbs as either states or events. The values for each indicator are computed automatically across a corpus of text. To improve classification performance, machine learning techniques are employed to combine multiple indicators. Three machine learning methods are compared for this task: decision tree induction, a genetic algorithm, and log-linear regres- sion.

This thesis develops a new approach to automatic language generation that focuses on the need to produce a range of different paraphrases from the same input representation. One novelty of the system is its solidly grounding representations of word meaning in a background knowledge base, which enables the production of paraphrases stemming from certain inferences, rather than from purely lexical relationships alone. The system is designed in such a way that the paraphrasing mechanism extends naturally to a multilingual generator; specifically, we will be concerned with producing English and German sentences. The focus of the system is on lexical paraphrases, and one of the contributions of the thesis is in identifying, analyzing and extending relevant linguistic research so that it can be used to handle...

this paper. Since transitive verbs necessarily have objects, a challenge for theories of transitivity is how to deal with the just-mentioned problems involving the semantic correlates of objecthood. In this paper I revisit these issues from a novel perspective, showing that the notion `object' of a transitive verb can be fruitfully explored in the context of recent work on the structure and representation of verb meaning and the licensing of arguments. Much recent research has converged on the notion `event' as an important organizing notion in the linguistic representation of meaning, and the grammatically-relevant component of a representation of verb meaning is now often called an `event structure' because its form is determined by the basic event type of the verb. I suggest that two distinct event structures can give rise to objects: a complex, causative event structure and a simple event structure. I argue that these two sources for objects shed light on some of the well-known challenges associated with the semantic underpinnings of objecthood. I use the transitive verbs of English to make these points, although I believe that the results of this research will largely generalize across languages (see section 4). 1. The `other' transitive verbs

This thesis is an investigation of the representation of lexical semantic information from a computational linguistic perspective. An implemented representation language is described which is not specic to lexical semantics, but is based on the use of typed feature structures augmented with default operations. This language, which is formally specied, allows the lexical semantic representations to be tightly integrated with the syntactic component of the lexical sign, capturing generalisations by use of inheritance, while allowing for exceptions with the default mechanism. Default inheritance and default unication are discussed in detail. Grammar rules and lexical rules can be specied in the same formalism and thus the paradigmatic treatment of lexical semantics can be integrated with an account at the syntagmatic level. The use of the language is illustrated with some examples of the representation of verbs, the treatment of logical metonymy and of sense extension. This is followe...

Verb alternations have been researched extensively in linguistics, but they have not yet received a systematic treatment in natural language generation systems; consequently, generators cannot make informed choices among alternatives. As a step towards overcoming this discrepancy, we review some linguistic work on several prominent alternations, revise and extend it, and suggest a set of rules that allow the series of alternated forms to be produced from a single base form of the verb, the lexical entry. The framework has been implemented in the Moose sentence generator, which can thus choose a particular verb alternation in order to accomplish generation goals such as placing emphasis on the most important element of the sentence.

This paper describes an approach to detect the organization of semantic subclasses of Japanese verbs. First, we classify verbs along two dimensions: thematic and aspectual. In the thematic dimension, we exploit the pattern of case marking particles which are attached to arguments of verbs. In the aspectual dimension, we exploit the classification of adverbs which modify verbs in a corpus. By combining the results of two classifications, we obtain an elaborate classification of verbs. We can incorporate the prototypicality of the members which constitute each semantic subclass by taking account of the frequency of case particles patterns and cooccurring adverbs. Moreover, the existence of close relationships among them enable us to detect the organization of these subclasses. Keywords: Japanese verbs, semantic subclass, two-dimensional, case marking particles, adverbs, prototypicality 1. INTRODUCTION

This paper presents a method for large corpus analysis to semantically classify an entire clause. In particular, we use cooccurrence statistics among similar clauses to determine the aspectual class of an input clause. The process examines linguistic features of clauses that are relevant to aspectual classification. A genetic algorithm determines what combinations of linguistic features to use for this task.

Seeminglysimpn expglyb?j3 may require an enriched form ofinterpb(59#IA pterpb(59 Verbs like began and finished can be used felicitously only when one of their arguments denotes an event (e.g., reading). However, such verbs commonlyapmon with nounpunb9U whose literalinterp5#A33b(5 denote entities (e.g., the book). It has been suggested that readers and listeners have to undertake additional comptionalb to interpb( strings like began the book that are not required when the book isinterpb(9A as an entity (e.g., Pustejovsky, 1995). If so, began the book should be harder topb559A than strings like read the book, when the verbdoes not require an argument that denotes an event, or strings like began the fight, when the argument denotes an event.Exp.bjAAW 1 found evidence from eye movements showing that entity nounpunbA3 take longer topbjUI? following verbs that require event arguments than verbs that do not.

This thesis proposes a strongly lexicalist approach to machine translation and applies it to the translation of spatial prepositions and prepositional expressions between English and Spanish. Bilingual contrastive knowledge resides solely in the bilingual lexicon and is structured in the form of correspondences between sets of source and target language lexemes related through indices. The resulting architecture maximizes the independence of the monolingual and bilingual components. This independence is demonstrated by developing a grammar of Spanish which is significantly different in its constructions from its analogous English grammar. In particular, relative clauses are analysed through a single rule that allows gaps in subject position, while clitic climbing and doubling are handled through mechanisms not normally found in grammatical descriptions of English. Bilingual lexical rules, in conjunction with the bilingual lexicon, constitute a single, motivated and well defined mechani...