Paper Info
Title
Joint and coupled bilingual topic model based sentence representations for language model adaptation
Abstract
This paper is concerned with data selection for adapting language model (LM) in statistical machine translation (SMT), and aims to find the LM training sentences that are topic similar to the translation task. Although the traditional approaches have gained significant performance, they ignore the topic information and the distribution information of words when selecting similar training sentences. In this paper, we present two bilingual topic model (BLTM) (joint and coupled BLTM) based sentence representations for cross-lingual data selection. We map the data selection task into cross-lingual semantic representations that are language independent, then rank and select sentences in the target language LM training corpus for a sentence in the translation task by the semanticsbased likelihood. The semantic representations are learned from the parallel corpus, with the assumption that the bilingual pair shares the same or similar distribution over semantic topics. Large-scale experimental results demonstrate that our approaches significantly outperform the state-of-the-art approaches on both LM perplexity and translation performance, respectively.
Year
Venue
Keywords
2013
IJCAI
translation task,sentence representation,statistical machine translation,data selection,lm training sentence,language model adaptation,cross-lingual data selection,bilingual topic model,target language lm training,translation performance,cross-lingual semantic representation,lm perplexity
Field
DocType
Citations 
Rule-based machine translation,Perplexity,Data selection,Computer science,Machine translation,Speech recognition,Natural language processing,Artificial intelligence,Topic model,Sentence,Machine learning,Language model
Conference
1
PageRank 
References 
Authors
0.35
23
5
Name
Order
Citations
PageRank
Shixiang Lu1193.39
Xiaoyin Fu2102.53
Wei Wei310.35
Xingyuan Peng441.46
Bo Xu524136.59