Luận văn Thạc sĩ Nguyễn Minh Thuận: Cải thiện hệ thống dịch máy VNU-UET

2018

55
0
0

Phí lưu trữ

30 Point

Mục lục chi tiết

1. Introduction

2. Literature review

2.1. History

2.2. Approaches

2.4. Open-Source Machine Translation

2.4.1. Moses - an Open Statistical Machine Translation System

2.4.2. OpenNMT - an Open Neural Machine Translation System

2.1. Monolingual Word Embedding Models

2.2. Cross-Lingual Word Embedding Models

3. Using Cross-Lingual Word Embedding Models for Machine Translation Systems

3.1. Enhancing the quality of Phrase-table in SMT Using Cross-Lingual Word Embedding

3.1.1. Recomputing Phrase-table weights

3.1.2. Generating new phrase pairs

3.2. Addressing the Unknown Word Problem in NMT Using Cross-Lingual Word Embedding Models

4. Experiments and Results

4.1. Word Translation Task

4.2. Impact of Enriching the Phrase-table on SMT system

4.3. Impact of Removing the Unknown Words on NMT system

5. Conclusion

Luận văn thạc sĩ vnu uet enhancing the quality of machine translation system using cross lingual word embedding models