This paper focuses on exploiting different models and methods in bilingual lexicon extraction, either from parallel or comparable corpora, in specialized domains. First, a special attention is given to the use of multilingual thesauri, and different search strategies based on such thesauri are investigated. Then, a method to combine the different models for bilingual lexicon extraction is prese...

This paper presents several methods for exploiting multiple resources in bilingual lexicon extraction, either from parallel or comparable corpora. First, a special attention is given to the use of multilingual thesauri, and different search strategies based on such thesauri are investigated. Then, a method to optimally combine the different resources for bilingual lexicon extraction is presente...

This research is aimed at developing a hierarchical alternation-based lexical architecture for machine translation. The proposed architecture makes extensive use of information sharing in describing valency frames through derivational links from base frames, rather than as independent entities. This has advantages in descriptive efficiency, robustness and maintainability. The lexicon being deve...

The great increase in work on the lexicon by computational and theoretical linguists throughout the s has concerned itself almost exclusively with monolingual lexicons Meanwhile applied work on multilingual lexicons mostly for machine translation MT has employed monolingual lexicons linked only at the level of semantics In this paper we argue that the traditional MT lexicon architecture while a...

Statistical approaches to text mining can be enhanced and improved through the qualitative representation of free text – ideally, a representation which accommodates ambiguity and imprecision. We introduce a specialized lexicon that assigns semantic categories to words, together with numeric values for centrality and intensity within each category. From this lexicon, we automatically generate a...

Off-line handwritten word/phrase recognition systems generally have monotonically cascaded architecture through several processing steps. In these architectures, the recognition engine follows a static model with a fixed feature space. Built-in resources are exhaustively used at each stage of the serial engine regardless of input complexity. However, the perception of a word is fundamentally an...

Current Address: GE Corporate Research and Development Schenectady, New York 12301 The hierarchical lexicon, in contrast to the traditional flat lexicon, enables a linguistic model to perform even in situations of incomplete knowledge: when a specific entry is missing, a more general entry can cover the gap. The question still remains regarding the construction of the lexicon itself. Since the ...

This paper proposes a new speech recognition scheme for foreign out-of-vocabulary words embedded in native-language speech. To recognize foreign names frequently observed in news speech or in translation speech, we adopted a hierarchical language model that had been successfully applied to OOV words covering native vocabularies. In this hierarchical language model, OOV vocabularies are modeled ...

Approaches to natural language processing that use a phrasal lexicon have the advantage of easily handling linguistic constructions that might otherwise be extragrammatical. However, current phrasal lexicons are often too rigid: their phrasal entries fail to cover the more flexible constructions. FLUSH, for Flexible Lexicon Utilizing Specialized and Hierarchical knowledge, is a knowledge-based ...