The Trouble with SMT Consistency
نویسندگان
چکیده
SMT typically models translation at the sentence level, ignoring wider document context. Does this hurt the consistency of translated documents? Using a phrase-based SMT system in various data conditions, we show that SMT translates documents remarkably consistently, even without document knowledge. Nevertheless, translation inconsistencies often indicate translation errors. However, unlike in human translation, these errors are rarely due to terminology inconsistency. They are more often symptoms of deeper issues with SMT models instead.
منابع مشابه
Rich Linguistic Features for Translation Memory-Inspired Consistent Translation
We improve translation memory (TM)inspired consistent phrase-based statistical machine translation (PB-SMT) using rich linguistic information including lexical, part-of-speech, dependency, and semantic role features to predict whether a TM-derived sub-segment should constrain PB-SMT translation. Besides better translation consistency, for English-to-Chinese Symantec TMs we report a 1.01 BLEU po...
متن کاملModeling Term Translation for Document-informed Machine Translation
Term translation is of great importance for statistical machine translation (SMT), especially document-informed SMT. In this paper, we investigate three issues of term translation in the context of documentinformed SMT and propose three corresponding models: (a) a term translation disambiguation model which selects desirable translations for terms in the source language with domain information,...
متن کاملA Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کاملDocument-level Consistency Verification in Machine Translation
Translation consistency is an important issue in document-level translation. However, the consistency in Machine Translation (MT) output is generally overlooked in most MT systems due to the lack of the use of document contexts. To address this issue, we present a simple and effective approach that incorporates document contexts into an existing Statistical Machine Translation (SMT) system for ...
متن کاملمحاسبۀ میزان خطای بیت در سیستم مخابراتی چندحاملی C-SMT
سیستم چندحاملی (Circular Staggered Multi-tone) C-SMT مدولاسیون پیشرفته است که دو سیستم SMT و (Generalized Frequency DivisionMultiplexing) GFDM را با موفقیت ترکیب کرده است. سیستم C-SMT بیشتر، مزایای سیستم‌های SMT و GFDM را حفظ کرده است و جایگزین مناسبی برای سیستم متداول (Orthogonal Frequency Division Multiplexing) OFDM به شمار می‌آید. در این مقاله میزان خطای بیت (BER) به‌طور تئوری، محاسبه و نشان...
متن کامل