Efficient Expansion of MT Rules using Corpora
نویسندگان
چکیده
منابع مشابه
Automatic Dictionary Expansion Using Non-parallel Corpora
Automatically generating bilingual dictionaries from parallel, manually translated texts is a well established technique that works well in practice. However, parallel texts are a scarce resource. Therefore, it is desirable also to be able to generate dictionaries from pairs of comparable monolingual corpora. For most languages, such corpora are much easier to acquire, and often in considerably...
متن کاملGeneralising Lexical Translation Strategies for MT Using Comparable Corpora
We report on an on-going research project aimed at increasing the range of translation equivalents which can be automatically discovered by MT systems. The methodology is based on semi-supervised learning of indirect translation strategies from large comparable corpora and their application in run-time to generate novel, previously unseen translation equivalents. This approach is different from...
متن کاملCDER: Efficient MT Evaluation Using Block Movements
Most state-of-the-art evaluation measures for machine translation assign high costs to movements of word blocks. In many cases though such movements still result in correct or almost correct sentences. In this paper, we will present a new evaluation measure which explicitly models block reordering as an edit operation. Our measure can be exactly calculated in quadratic time. Furthermore, we wil...
متن کاملUsing local rules for disambiguation of homographs in Hungarian corpora
The historical corpus of Hungarian contains about 20 million running words at the moment. To be able to retrieve the occurrences of the lexemes, a morphological analyser programme was developed which is able to segment the running words and identifies the lexeme and the suffixes. Over 30% of the running words can have more then one correct analysis. Therefore we are aiming to develop methods fo...
متن کاملProceedings of the MT Summit XI Workshop Using Corpora for Natural Language Generation: Language Generation and Machine Translation (UCNLG+MT)
This paper presents a new method of evaluation for generation and parsing components of transfer-based MT systems where the transfer rules have been automatically acquired from parsed sentence-aligned bitext corpora. The method provides a means of quantifying the upper bound imposed on the MT system by the quality of the parsing and generation technologies for the target language. We include ex...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Natural Language Processing
سال: 2006
ISSN: 1340-7619,2185-8314
DOI: 10.5715/jnlp.13.2_63