Levin’s (1993) study of verb classes is a widely used resource for lexical semantics. In her framework, some verbs, such as give, exhibit no class ambiguity. But other verbs, such as write, have several alternative classes. We extend Levin’s inventory to a simple statistical model of verb class ambiguity. Using this model we are able to generate preferences for ambiguous verbs without the use of a disambiguated corpus. We additionally show that these preferences are useful as priors for a verb sense disambiguator.

We focus on the problem of building large repositories of lexical conceptual structure (LCS) representations for verbs in multiple languages. One of the main results of this work is the definition of a relation between broad semantic classes and LCS meaning components. Our acquisition program---LEXICALL---takes, as input, the result of previous work on verb classification and thematic grid tagging, and outputs LCS representations for different languages. These representations have been ported into English, Arabic and Spanish lexicons, each containing approximately 9000 verbs. We are currently using these lexicons in an operational foreign language tutoring and machine translation. 1 Introduction A wide range of new capabilities in NLP applications such as foreign language tutoring (FLT) has been made possible by recent advances in lexical semantics (Carrier and Randall, 1993; Dowty, 1991; Fillmore, 1968; Foley and Van Valin, 1984; Grimshaw, 1990; Gruber, 1965; Hale and Keyser, 1993; ...

Abstract not found

In contrast to current intelligent systems, which must be laboriously programmed for each task they are meant to perform, instructable agents can be taught new tasks and associated knowledge. This thesis presents a general theory of learning from tutorial instruction and its use to produce an instructable agent. Tutorial instruction is a particularly powerful form of instruction, because it allows the instructor to communicate whatever kind of knowledge a student needs at whatever point it is needed. To exploit this broad flexibility, however, a tutorable agent must support a full range of interaction with its instructor to learn a full range of knowledge. Thus, unlike most machine learning tasks, which target deep learning of a single kind of knowledge from a single kind of input, tutorability requires a breadth of learning from a broad range of instructional interactions. The theory of learning from tutorial...

This paper discusses research on distinguishing word meanings in the context of information retrieval systems. We conducted experiments with three sources of evidence for making these distinctions: morphology, part-of-speech, and phrases. We have focused on the distinction between homonymy and polysemy (unrelated vs. related meanings). Our results support the need to distinguish homonymy and polysemy. We found: 1) grouping morphological variants makes a significant improvement in retrieval performance, 2) that more than half of all words in a dictionary that differ in part-of-speech are related in meaning, and 3) that it is crucial to assign credit to the component words of a phrase. These experiments provide a better understanding of word-based methods, and suggest where natural language processing can provide further improvements in retrieval performance. 1

This study investigated whether different lexicalization patterns of motion events in English and Spanish predict how speakers of these languages perform in non-linguistic tasks. Using 36 motion events, we compared English and Spanish speakers' linguistic descriptions to their performance on two non-linguistic tasks: recognition memory and similarity judgments. We investigated the effect of language processing on non-linguistic performance by varying the nature of the encoding before testing for recognition and similarity. Participants encoded the events while describing them verbally or not. No effect of language was obtained in the recognition memory task after either linguistic or non-linguistic encoding and in the similarity task after non-linguistic encoding. We did find a linguistic effect in the similarity task after verbal encoding, an effect that conformed to languagespecific patterns. Linguistic descriptions directed attention to certain aspects of the events later used to make a non-linguistic judgment. This suggests that linguistic and non-linguistic performance are dissociable, but language-specific regularities made available in the experimental context may mediate the speaker's performance in specific tasks.

Natural language reports generated by existing systems ignore the historical context of the facts and events they relate. In this paper, I argue that going beyond this limitation requires abandoning the pipelined architecture of existing report generators. I propose a new architecture in which a first draft of the report is organized around new information and then incrementally revised to opportunistically add related historical information. This type of information-adding revision allows to elaborate inside a clause or a nominal while taking into account surface structure constraints from any other portion of the report. In addition to providing the additional flexibility required to convey historical information, the proposed architecture constitutes an interesting testbed to investigate a wide range of open questions concerning content planning below the sentence level, generation with revision and generation architecture. 1 Introduction: generating reports in their historical co...

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...

. This paper describes and discusses some theoretical and practical problems arising from developing a system to combine the structured but incomplete information from machine readable dictionaries (MRDs) with the unstructured but more complete information available in corpora for the creation of a bilingual lexical data base, presenting a methodology to integrate information from both sources into a single lexical data structure. The bicord system (BIlingual CORpus-enhanced Dictionaries) involves linking entries in Collins English-French and FrenchEnglish bilingual dictionary with a large English-French and French-English bilingual corpus. We have concentrated on the class of action verbs of movement, building on earlier work on lexical correspondences specific to this verb class between languages (Klavans and Tzoukermann, 1989), (Klavans and Tzoukermann, 1990a), (Klavans and Tzoukermann, 1990b). 1 We first examine the way prototypical verbs of movement are translated in the Collin...

The paper presents a prototype lexicalist Machine Translation system (based on the so-called `Shake-and-Bake' approach of Whitelock (1992)) consisting of an analysis component, a dynamic bilingual lexicon, and a generation component, and shows how it is applied to a range of MT problems. Multi-Lexeme translations are handled through bi-lexical rules which map bilingual lexical signs into new bilingual lexical signs. It is argued that much translation can be handled by equating translationally equivalent lists of lexical signs, either directly in the bilingual lexicon, or by deriving them through bi-lexical rules. Lexical semantic information organized as Qualia structures (Pustejovsky 1991) is used as a mechanism for restricting the domain of the rules. 1 Introduction Transfer based approaches to machine translation (MT) involve three main phases: analysis, transfer and generation. During analysis, the syntactic and semantic structure of a sentence is made explicit through a source la...