VIETNAM NATIONAL UNIVERISTY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGY NGUYEN MINH THUAN Enhancing the quality of Machine Translation System Using Cross-Lingual Word Embedding Models (Nâng cao chất lượng của hệ thống dịch máy dựa trên các mô hình vector nhúng biểu diễn từ giữa hai ngôn ngữ) Program: Computer Science Major: Computer Science Code: 8480101.01 MASTER THESIS: COMPUTER SCIENCE SUPERVISOR: Assoc. NGUYEN PHUONG THAI Hanoi – 11/2018 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com Enhancing the quality of Machine Translation System Using Cross-Lingual Word Embedding Models Nguyen Minh Thuan Faculty of Information Technology University of Engineering and Technology Vietnam National University, Hanoi Supervised by Associate Professor. Nguyen Phuong Thai A thesis submitted in fulfillment of the requirements for the degree of Master of Science in Computer Science November 2018 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com 2 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com ORIGINALITY STATEMENT ‘I hereby declare that this submission is my own work and to the best of my knowledge it contains no materials previously published or written by another person, or substan- tial proportions of material which have been accepted for the award of any other degree or diploma at University of Engineering and Technology (UET/Coltech) or any other educational institution, except where due acknowledgement is made in the thesis. Any contribution made to the research by others, with whom I have worked at UET/Coltech or elsewhere, is explicitly acknowledged in the thesis.
I also declare that the intellectual content of this thesis is the product of my own work, except to the extent that assistance from others in the project’s design and conception or in style, presentation and linguistic expression is acknowledged.’ Hanoi, November 15th , 2018 Signed. i LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com ii ABSTRACT In recent years, Machine Translation has shown promising results and received much interest of researchers. Two approaches that have been widely used for machine trans- lation are Phrase-based Statistical Machine Translation (PBSMT) and Neural Ma- chine Translation (NMT). During translation, both approaches rely heavily on large amounts of bilingual corpora which require much effort and financial support.
The lack of bilingual data leads to a poor phrase-table, which is one of the main compo- nents of PBSMT, and the unknown word problem in NMT. In contrast, monolingual data are available for most of the languages. Thanks to the advantage, many models of word embedding and cross-lingual word embedding have been appeared to improve the quality of various tasks in natural language processing. The purpose of this thesis is to propose two models for using cross-lingual word embedding models to address the above impediment.
The first model enhances the quality of the phrase-table in SMT, and the remaining model tackles the unknown word problem in NMT. Publications: ? Minh-Thuan Nguyen, Van-Tan Bui, Huy-Hien Vu, Phuong-Thai Nguyen and Chi-Mai Luong. Enhancing the quality of Phrase-table in Statistical Machine Translation for Less-Common and Low-Resource Languages. In the 2018 International Conference on Asian Language Processing (IALP 2018).
LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com iii ACKNOWLEDGEMENTS I would like to express my sincere gratitude to my lecturers in university, and especially to my supervisors - Assoc. Nguyen Phuong Thai, Dr. Nguyen Van Vinh and MSc. Vu Huy Hien.
They are my inspiration, guiding me to get the better of many obstacles in the completion this thesis. I am grateful to my family. They usually encourage, motivate and create the best conditions for me to accomplish this thesis. I would like to also thank my brother, Nguyen Minh Thong, my friends, Tran Minh Luyen, Hoang Cong Tuan Anh, for giving me many useful advices and supporting my thesis, my studying and my living.
Finally, I sincerely acknowledge the Vietnam National University, Hanoi and especially, TC.02-2016-03 project named “Building a machine translation system to support translation of documents between Vietnamese and Japanese to help managers and businesses in Hanoi approach Japanese market” for supporting finance to my master study. LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com To my family ♥ iv LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com Table of Contents 1 Introduction 1 2 Literature review 4 2.4 Open-Source Machine Translation .1 Moses - an Open Statistical Machine Translation System .2 OpenNMT - an Open Neural Machine Translation System .1 Monolingual Word Embedding Models .2 Cross-Lingual Word Embedding Models. 13 3 Using Cross-Lingual Word Embedding Models for Machine Trans- lation Systems 17 3.1 Enhancing the quality of Phrase-table in SMT Using Cross-Lingual Word Embedding .1 Recomputing Phrase-table weights .2 Generating new phrase pairs .2 Addressing the Unknown Word Problem in NMT Using Cross-Lingual Word Embedding Models. 21 4 Experiments and Results 27 4.
31 v LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com TABLE OF CONTENTS vi 4.1 Word Translation Task .2 Impact of Enriching the Phrase-table on SMT system .3 Impact of Removing the Unknown Words on NMT system. 35 5 Conclusion 38 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com List of Figures 2.1 The CBOW model predicts the current word based on the context, and the Skip-gram predicts surrounding words based on the current word.2 Toy illustration of the cross-lingual embedding model.1 Flow of training phrase.2 Flow of testing phrase.3 Example in testing phrase. 25 vii LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com List of Tables 3.1 The sample of new phrase pairs generated by using projections of word vector representations .4 The precision of word translation retrieval top-k nearest neighbors in Vietnamese-English and Japanese-Vietnamese language pairs.5 Results on UET and TED dataset in the PBSMT system for Vietnamese- English and Japanese-Vietnamese respectively .6 Translation examples of the PBSMT in Vietnamese-English .7 Results of removing unknown words on UET and TED dataset in the NMT system for Vietnamese-English and Japanese-Vietnamese respectively .8 Translation examples of the NMT system in Vietnamese-English. 37 viii LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com List of Abbreviations MT Machine Translation SMT Statistical Machine Translation PBSMT Phrase-based Statistical Machine Translation NMT Neural Machine Translation NLP Natural Language Processing RNN Recurrent Neural Network CNN Convolutional Neural Network UNMT Unsupervised Neural Machine Translation ix LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com Chapter 1 Introduction Machine Translation (MT) is a sub-field of computational linguistics.
It is auto- mated translation, which translates text or speech from one natural language to another by using computer software. Nowadays, machine translation systems attain much success in practice, and two approaches that have been widely used for MT are Phrase-based statistical machine translation (PBSMT) and Neural Machine Trans- lation (NMT). In the PBSMT system, the core of this system is the phrase-table, which contains words and phrases for SMT system to translate. In the translation process, sentences are split into distinguished parts as shown in (Koehn et al.
At each step, for a given source phrase, the system will try to find the best candidate amongst many target phrases as its translation based mainly on phrase-table. Hence, having a good phrase-table possibly makes translation systems improve the quality of translation. However, attaining a rich phrase-table is a chal- lenge since the phrase-table is extracted and trained from large amounts of bilingual corpora which require much effort and financial support, especially for less-common languages such as Vietnamese, Laos, etc. In the NMT system, two main components are encoder and decoder.
the encoder component uses a neural network, such as the recurrent neural network (RNN), to encode the source sentence, and the decoder component also uses a neural network to predict words in the target language. Some NMT models incorporate attention mechanisms to improve the translation quality. To reduce the computational complexity, conventional NMT systems often limit their vocabularies to be the top 30K-80K most frequent words in the source and target language, and all words outside the vocabulary, called unknown words, are replaced into a single unk symbol. This approach leads to the inability to generate 1 LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com 2 the proper translation for this unknown words during testing as shown in (Luong et al., 2015b) (Li et al., 2016) Latterly, there are several approaches to address the above impediments.
With the problem in the PBSMT system. (Passban et al., 2016) proposed a method of using new scores generated by a Convolution Neural Network which indicates the se- mantic relatedness of phrase pairs. They attained an improvement of approximately 0. However, their method is suitable for medium-size corpora and creates more scores for the phrase-table which can increase computation complexity of all translation systems.
(Cui et al., 2013) utilized techniques of pivot languages to enrich their phrase-table. Their phrase-table is made of source-pivot and pivot-target phrase-tables. As a result of this combination, they attained a significant improvement of translation. Similarly, (Zhu et al., 2014) used a method based on pivot languages to calculate the translation probabilities of source-target phrase pairs and achieved a slight enhance- ment.
Unfortunately, the methods based on pivot languages are not able to apply for the Vietnamese language since the the less-common nature of this language. (Vogel and Monson, 2004) improved the translation quality by using phrase pairs from an augmented dictionary. They first augmented the dictionary using simple morphological variations and then assigned probabilities to entries of this dictionary by using co-occurrence frequencies collected from bilingual data. However, their method needs a lot of bilingual corpora to estimate accurately the probabilities for dictionary entries, which are not available for low-resource languages.
In order to address the unknown word problem in NMT system. (Luong et al., 2015b) annotated the training bilingual corpus with explicit alignment information that allows the NMT system to emit, for each unknown word in the target sentence, the position of its corresponding word in the source sentence. This information is then used in a post-processing step to translate every unknown word by using a bilingual dictionary. The method showed a substantial improvement of up to 2.8 BLEU points over various NMT systems on WMT’14 English-French translation task.
However, having the good dictionary, which is utilized in the post-processing step, is also costly and time-consuming. (Sennrich et al., 2016) introduced a simple approach to handle the translation of unknown words in NMT by encoding unknown words as a sequence of subword units. This method based on the intuition that a variety of word classes are translated via smaller units than words. For example, names are translated by character copying or LUAN VAN CHAT LUONG download : add luanvanchat@agmail.com 3 transliteration, compounds are translated via compositional translation, etc.
The approach indicated an improvement up to 1.3 BLEU over a back-off dictionary baseline model on WMT 15 English-Russian translation task. (Li et al., 2016) proposed a novel substitution-translation-restoration method to tackle the problem of the NMT unknown word. In this method, the substitution step replaces the unknown words in a testing sentence with similar in-vocabulary words based on a similarity model learned from monolingual data. The translation step then translates the testing sentence with a model trained on bilingual data with unknown words replaced.
Finally, the restoration step substitutes the translations of the replaced words by that of original ones. This method demonstrated a significant improvement up to 4 BLEU points over the attention-based NMT on Chinese-to- English translation. Recently, techniques using word embedding receive much interest from natural language processing communities. Word embedding is a vector representation of words which conserves semantic information and their contexts words.
Additionally, we can exploit the advantage of embedding to represent words in diverse distinction spaces as shown in (Mikolov et al. Besides, cross-lingual word embedding models are also receiving a lot of interest, which learn cross-lingual representations of words in a joint embedding space to represent meaning and transfer knowledge in cross-lingual scenarios. Inspired by the advantages of the cross-lingual embedding models, the work of (Mikolov et al., 2013b) and (Li et al.