Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1570–1579 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 1570 Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences Xiangyu Duan1, Baijun Ji1, Hao Jia1, Min Tan1, Min Zhang1∗, Boxing Chen2, Weihua Luo2, Yue Zhang3 1 Institute of Aritificial Intelligence, School of Computer Science and Technology, Soochow university 2 Alibaba DAMO Academy 3 School of Engineering, Westlake University {xiangyuduan,minzhang}@suda.edu.cn; {bjji,hjia,mtan2017}@stu.suda.edu.cn; {boxing.cbx,weihua.luowh}@alibaba-inc.com; yue.zhang@wias.org.cn Abstract In this paper, we propose a new task of ma- chine translation (MT), which is based on no parallel sentences but can refer to a ground- truth bilingual dictionary. Motivated by the ability of a monolingual speaker learning to translate via looking up the bilingual dictio- nary, we propose the task to see how much potential an MT system can attain using the bilingual dictionary and large scale monolin- gual corpora, while is independent on paral- lel sentences. We propose anchored train- ing (AT) to tackle the task. AT uses the bilingual dictionary to establish anchoring points for closing the gap between source language and target language. Experiments on various language pairs show that our ap- proaches are significantly better than various baselines, including dictionary-based word-by- word translation, dictionary-supervised cross- lingual word embedding transformation, and unsupervised MT. On distant language pairs that are hard for unsupervised MT to perform well, AT performs remarkably better, achiev- ing performances comparable to supervised SMT trained on more than 4M parallel sen- tences1 . 1 Introduction Motivated by a monolingual speaker acquiring translation ability by referring to a bilingual dic- tionary, we propose a novel MT task that no par- allel sentences are available, while a ground-truth bilingual dictionary and large-scale monolingual corpora can be utilized. This task departs from unsupervised MT task that no parallel resources, including the ground-truth bilingual dictionary, are allowed to utilize (Artetxe et al., 2018c; Lam- ple et al., 2018b). This task is also distinct to ∗ Corresponding Author. 1Code is available at https://github.com/ mttravel/Dictionary-based-MT supervised/semi-supervised MT task that mainly depends on parallel sentences (Bahdanau et al., 2015; Gehring et al., 2017; Vaswani et al., 2017; Chen et al., 2018; Sennrich et al., 2016a). The bilingual dictionary is often utilized as a seed in bilingual lexicon induction (BLI) that aims to induce more word pairs within the language pair (Mikolov et al., 2013). Another utilization of the bilingual dictionary is for translating low- frequency words in supervised NMT (Arthur et al., 2016; Zhang and Zong, 2016). We are the first to utilize the bilingual dictionary and the large scale monolingual corpora to see how much potential an MT system can achieve without using parallel sentences. This is different from using artificial bilingual dictionaries generated by unsupervised BLI for initializing an unsupervised MT system (Artetxe et al., 2018c,b; Lample et al., 2018a), we use the ground-truth bilingual dictionary and apply it throughout the training process. We propose Anchored Training (AT) to tackle this task. Since word representations are learned over monolingual …

Content truncated to 500 words