Machine Translation without Words through Substring Alignment

In this paper, we demonstrate that accurate machine translation is possible without the concept of “words,” treating MT as a problem of transformation between character strings. We achieve this result by applying phrasal inversion transduction grammar alignment techniques to character strings to train a character-based translation model, and using this in the phrase-based MT framework. We also propose a look-ahead parsing algorithm and substring-informed prior probabilities to achieve more effective and efficient alignment. In an evaluation, we demonstrate that character-based translation can achieve results that compare to word-based systems while effectively translating unknown and uncommon words over several language pairs.

• Type: Journal
• Year: 2012
• Where: ACL
• Authors: Graham Neubig, Taro Watanabe, Shinsuke Mori, Tatsuya Kawahara
• Keywords: ACL 2012, Alignment Techniques, Computational Linguistics, Language Pairs, Translation Model