Improving a Statistical MT System with Automatically Learned Rewrite Patterns
نویسندگان
چکیده
• Limitation of current phrase-based SMT • No mechanism for expressing and using linguistic phrases in reordering • Ordering of target words do not respect linguistic phrase boundaries • Xia and McCord’s solution: • Extract linguistic rewrite rules from corpora • Preprocess source sentences so phrase ordering is similar to that of target language • Perform SMT decoding with monotonic ordering constraint
منابع مشابه
Learned rewrite rules versus learned search control rules to improveplan qualityMuhammad
Domain independent planners can produce better-quality plans through the use of domain-dependent knowledge , typically encoded as search control rules. The planning-by-rewriting approach has been proposed as an alternative technique for improving plan quality. We present a system called Sys-REWRITE that automatically learns plan rewriting rules and compare it with Sys-SEARCH-CONTROL, a system t...
متن کاملModular MT with a Learned Bilingual Dictionary: Rapid Deployment of a New Language Pair
The MT system described in this paper combines hand-built analysis and generation components with automatically learned example-based transfer patterns. Up to now, the transfer component used a traditional bilingual dictionary to seed the transfer pattern learning process and to provide fallback translations at runtime. This paper describes an improvement to the system by which the bilingual di...
متن کاملUsing Multiple Edit Distances to Automatically Rank Machine Translation Output
This paper addresses the challenging problem of automatically evaluating output from machine translation (MT) systems in order to support the developers of these systems. Conventional approaches to the problem include methods that automatically assign a rank such as A, B, C, or D to MT output according to a single edit distance between this output and a correct translation example. The single e...
متن کاملLearning Transfer Rules for Machine Translation with Limited Data
The transfer-based approach to machine translation (MT) captures structural transfers between the source language and the target language, with the goal of producing grammatical translations. The major drawback of the approach is the development bottleneck, requiring many human-years of rule development. On the other hand, data-driven approaches such as example-based and statistical MT achieve ...
متن کاملLearning Rewrite Rules versus Search Control Rules to Improve Plan Quality
Domain independent planners can produce better-quality plans through the use of domain-speci c knowledge, typically encoded as search control rules. The planning-by-rewriting approach has been proposed as an alternative technique for improving plan quality. We present a system that automatically learns plan rewriting rules and compare it with a system that automatically learns search control ru...
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 2004