منابع مشابه
Comparative Evaluation of Online Machine Translation Systems with Legal Texts*
The authors discuss both the proper use of available online machine translation (MT) technologies for law library users and their comparative evaluation of the performance of a number of representative online MT systems in translating legal texts from various languages into English. They evaluated a large-scale corpus of legal texts by means of BLEU/NIST scoring, a de facto standard way of exer...
متن کاملLegal translators and legal translation
Since I am a lawyer, let me start with a disclaimer: nothing I shall say is intended to reflect the views of my employers past or present or any professional association to which I may belong. And please don’t write any letters — unless they are addressed to me. The reason I start in this fashion is that some years ago, when I had just become a notary, I gave an interview to a charming lady fro...
متن کاملCultural Frame and Translation of Pronominal Adverbs in Legal English
This paper explores the relationship between cultural knowledge and the specific meaning of a pronominal adverb in legal English where Chinese translators need to get the correct translation in their venture into translating the language of law. On the one hand, relying on the relevant legal cultural knowledge functioning as domain-general reference within a community or jurisdiction, tra...
متن کاملOnline Large-Margin Training of Syntactic and Structural Translation Features
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimize. Building on the work of Watanabe et al., we explore the use of the MIRA algorithm of Crammer et al. as an alternative to MERT. We first show that by parallel processing and exploiting more of the parse forest, we c...
متن کاملOnline Large-Margin Training for Statistical Machine Translation
We achieved a state of the art performance in statistical machine translation by using a large number of features with an online large-margin training algorithm. The millions of parameters were tuned only on a small development set consisting of less than 1K sentences. Experiments on Arabic-toEnglish translation indicated that a model trained with sparse binary features outperformed a conventio...
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: Babel
سال: 2016
ISSN: 0521-9744,1569-9668
DOI: 10.1075/babel.62.3.06bes