Post-editing neural machine translation versus translation memory segments
نویسندگان
چکیده
منابع مشابه
Online Learning for Neural Machine Translation Post-editing
Neural machine translation has meant a revolution of the field. Nevertheless, postediting the outputs of the system is mandatory for tasks requiring high translation quality. Post-editing offers a unique opportunity for improving neural machine translation systems, using online learning techniques and treating the post-edited translations as new, fresh training data. We review classical learnin...
متن کاملRanking Machine Translation Systems via Post-editing
In this paper we investigate ways in which information from the postediting of machine translations can be used to rank translation systems for quality. In addition to the commonly used edit distance between the raw translation and its edited version, we consider post-editing time and keystroke logging, since these can account not only for technical effort, but also cognitive effort. In this sy...
متن کاملComparing forum data post-editing performance using translation memory and machine translation output: a pilot study
In this paper we present the results from a pilot study undertaken with translation students to compare community forum content post-editing performance based on suggestions from different translation systems. Output from both Translation Memory (TM) and Statistical Machine Translation (SMT) was presented to participants in the ACCEPT online postediting environment, where they needed to perform...
متن کاملMemory-augmented Neural Machine Translation
Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memoryaugmented NMT (M-NMT) architecture, which stores knowledge about how words (usually infrequently encountered ones) should be translated in a memory and then utilizes...
متن کاملA machine translation system combining rule-based machine translation and statistical post-editing
System architecture, experimental settings and evaluation results of the EIWA in the WAT2014 Japanese to English (jaen) and Chinese to Japanese (zh-ja) tasks are described. Our system is combining rule-based machine translation (RBMT) and statistical post-editing (SPE). Evaluation results for ja-en task show 19.86 BLEU score, 0.7067 RIBES score, and 22.50 human evaluation score. Evaluation resu...
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: Machine Translation
سال: 2019
ISSN: 0922-6567,1573-0573
DOI: 10.1007/s10590-019-09232-x