Translation By Structural Correspondences
نویسندگان
چکیده
We sketch and illustrate an approach to machine translation that exploits the potential of simultaneous correspondences between separate levels of linguistic representation, as formalized in the LFG notion of codescriptions. The approach is illustrated with examples from English, German and French where the source and the target language sentence show noteworthy differences in linguistic analysis.
منابع مشابه
Finding Structural Correspondences from Bilingual Parsed Corpus for Corpus-based Translation
In this paper, we describe a system and methods for finding structural correspondences from the paired dependency structures of a source sentence and its translation in a target language. The system we have developed finds word correspondences first, then finds phrasal correspon(tences based on word correspondences. We have also developed a GUI system with which a user can check and correct til...
متن کاملRestricting Bidirectional Translation Correspondences to the Appropriate Context
This paper addresses the resolution of translational ambiguities in a lexicalist transfer approach, which is realized in the translation system Verbmobll. It is particularly concerned with the use of various kinds of constraints that restrict the translation mapping of ambiguous lexical items to the appropriate context. They range from structural, semantic and prosodic information to discourse ...
متن کاملAn experiment on synchronous TAGs for the construction of a transfer module
This paper presents some considerations on the use of Synchronous T AGs for the design of a structural transfer module, which is the main component of transfer-based systems for Machine Translation. The transfer module establishes the correspondences between the structural representation of both the source and target languages. A study of a corpus from Economics was carried out in order to defi...
متن کاملAutomat ic Extraction of Word Sequence Correspondences in Parallel Corpora
This paper proposes a method of finding correspondences of arbitrary length word sequences in aligned parallel corpora of Japanese and English. Translation candidates of word sequences are evaluated by a similarity measure between the sequences defined by the co-occurrence frequency and independent frequency of the word sequences. The similarity measure is an extension of Dice coefficient. An i...
متن کاملAutomatic Extraction of Word Sequence Correspondences in Parallel Corpora
This paper proposes a method of finding correspondences of arbitrary length word sequences in aligned parallel corpora of Japanese and English. Translation candidates of word sequences are evaluated by a similarity measure between the sequences defined by the co-occurrence frequency and independent frequency of the word sequences. The similarity measure is an extension of Dice coefficient. An i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1989