For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Paraphrase Lattice for Statistical Machine Translation
Takashi ONISHI Masao UTIYAMA Eiichiro SUMITA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/06/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Natural Language Processing
statistical machine translation, lattice decoding, paraphrasing, paraphrase lattice,
Full Text: PDF(272.6KB)>>
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.