Combining translation memories and statistical machine translation using sparse features

• Published in: Machine translation Vol. 30; no. 3/4; pp. 183 - 202
• Main Authors: Li, Liangyou, Escartín, Carla Parra, Way, Andy, Liu, Qun
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer 01-12-2016; Springer Netherlands; Springer Nature B.V
• Subjects: Artificial Intelligence; Computational Linguistics; Computer memory; Computer Science; Decoding; English language; Feature extraction; French language; Machine translation; Natural Language Processing (NLP); Phrases; Spanish language; Syntax; Run-time combination; Statistical machine translation; Sparse feature; Translation memory; Fuzzy match
• ISSN: 0922-6567; 1573-0573
• DOI: 10.1007/s10590-016-9187-6

The combination of translation memories (TMs) and statistical machine translation (SMT) has been demonstrated to be beneficial. In this paper, we present a combination approach which integrates TMs into SMT by using sparse features extracted at run-time during decoding. These features can be used on both phrase-based SMT and syntax-based SMT. We conducted experiments on a publicly available English-French data set and an English-Spanish industrial data set. Our experimental results show that these features significantly improve our phrase-based and syntax-based SMT baselines on both language pairs.