Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo khoa học: "Automated semantic assistance for translators"

The problem we address in this paper is that of providing contextual examples of translation equivalents for words from the general lexicon using comparable corpora and semantic annotation that is uniform for the source and target languages. For a sentence, phrase or a query expression in the source language the tool detects the semantic type of the situation in question and gives examples of similar contexts from the target language corpus. | ASSIST Automated semantic assistance for translators Serge Sharoff Bogdan Babych Centre for Translation Studies University of Leeds LS2 9JT UK s.sharoff b.babych @leeds.ac.uk Paul Rayson Olga Mudraya Scott Piao UCREL Computing Department Lancaster University LA1 4WA UK p.rayson o.moudraia s.piao @lancs.ac.uk Abstract The problem we address in this paper is that of providing contextual examples of translation equivalents for words from the general lexicon using comparable corpora and semantic annotation that is uniform for the source and target languages. For a sentence phrase or a query expression in the source language the tool detects the semantic type of the situation in question and gives examples of similar contexts from the target language corpus. 1 Introduction It is widely acknowledged that human translators can benefit from a wide range of applications in computational linguistics including Machine Translation Carl and Way 2003 Translation Memory Planas and Furuse 2000 etc. There have been recent research on tools detecting translation equivalents for technical vocabulary in a restricted domain e.g. Dagan and Church 1997 Bennison and Bowker 2000 . The methodology in this case is based on extraction of terminology both single and multiword units and alignment of extracted terms using linguistic and or statistical techniques Déjean et al. 2002 . In this project we concentrate on words from the general lexicon instead of terminology. The rationale for this focus is related to the fact that translation of terms is should be stable while general words can vary significantly in their translation. It is important to populate the terminological database with terms that are missed in dictionaries or specific to a problem domain. However once the translation of a term in a domain has been identified stored in a dictionary and learned by the translator the process of translation can go on without consulting a dictionary or a corpus. In contrast words from the general