Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1024–1033, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Agreement-based Learning of Parallel Lexicons and Phrases from Non-Parallel Corpora Chunyang Liu†, Yang Liu†#∗, Huanbo Luan†, Maosong Sun†#, and Heng Yu‡ † State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China # Jiangsu Collaborative Innovation Center for Language Competence, Jiangsu, China ‡ Samsung R&D Institute of China, Beijing 100028, China {liuchunyang2012,liuyang.china,luanhuanbo}@gmail.com, sms@tsinghua.edu.cn h0517.yu@samsung.com Abstract We introduce an agreement-based ap- proach to learning parallel lexicons and phrases from non-parallel corpora. The basic idea is to encourage two asym- metric latent-variable translation models (i.e., source-to-target and target-to-source) to agree on identifying latent phrase and word alignments. The agreement is de- fined at both word and phrase levels. We develop a Viterbi EM algorithm for jointly training the two unidirectional models ef- ficiently. Experiments on the Chinese- English dataset show that agreement- based learning significantly improves both alignment and translation performance. 1 Introduction Parallel corpora, which are large collections of parallel texts, serve as an important resource for inducing translation correspondences, either at the level of words (Brown et al., 1993; Smadja and McKeown, 1994; Wu and Xia, 1994) or phrases (Kupiec, 1993; Melamed, 1997; Marcu and Wong, 2002; Koehn et al., 2003). However, the availabil- ity of large-scale, wide-coverage corpora still re- mains a challenge even in the era of big data: par- allel corpora are usually only existent for resource- rich languages and restricted to limited domains such as government documents and news articles. Therefore, intensive attention has been drawn to exploiting non-parallel corpora for acquiring translation correspondences. Most previous ef- forts have concentrated on learning parallel lexi- cons from non-parallel corpora, including parallel sentence and lexicon extraction via bootstrapping (Fung and Cheung, 2004), inducing parallel lexi- cons via canonical correlation analysis (Haghighi ∗Corresponding author: Yang Liu. et al., 2008), training IBM models on monolin- gual corpora as decipherment (Ravi and Knight, 2011; Nuhn et al., 2012; Dou et al., 2014), and deriving parallel lexicons from bilingual word em- beddings (Vuli´c and Moens, 2013; Mikolov et al., 2013; Vuli´c and Moens, 2015). Recently, a number of authors have turned to a more challenging task: learning parallel phrases from non-parallel corpora (Zhang and Zong, 2013; Dong et al., 2015). Zhang and Zong (2013) present a method for retrieving parallel phrases from non-parallel corpora using a seed parallel lexicon. Dong et al. (2015) continue this line of research to further introduce an iterative ap- proach to joint learning of parallel lexicons and phrases. They introduce a corpus-level latent- variable translation model in a non-parallel sce- nario and develop a training algorithm that alter- nates between (1) using a parallel lexicon to ex- tract parallel phrases from non-parallel corpora and (2) using the extracted parallel phrases to en- large the parallel lexicon. They show that starting from a small seed lexicon, their …

Content truncated to 500 words