relation: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3413/
title: Enhancing the quality of Phrase-table in Statistical Machine Translation for Less-Common and Low-Resource Languages
creator: Nguyen, Minh Thuan
creator: Bui, Van Tan
creator: Vu, Huy Hien
creator: Nguyen, Phuong Thai
creator: Luong, Chi Mai
subject: Information Technology (IT)
description: The phrase-table plays an important role in traditional phrase-based statistical machine translation (SMT) system. During translation, a phrase-based SMT system relies heavily on phrase-table to generate outputs. In this paper, we propose two methods for enhancing the quality of phrase-table. The first method is to recompute phrasetable weights by using vector representations similarity. The remaining method is to enrich the phrase-table by  integrating new phrase-pairs from an extended dictionary  and projections of word vector presentations on the target language space. Our methods produce an attainment of up to  0.21 and 0.44 BLEU scores on in-domain and cross-domain  (Asian Language Treebank - ALT) English - Vietnamese  datasets respectively.
date: 2018
type: Conference or Workshop Item
type: NonPeerReviewed
format: application/pdf
language: en
identifier: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3413/1/30.pdf
identifier:   Nguyen, Minh Thuan and Bui, Van Tan and Vu, Huy Hien and Nguyen, Phuong Thai and Luong, Chi Mai  (2018) Enhancing the quality of Phrase-table in Statistical Machine Translation for Less-Common and Low-Resource Languages.  In: International Association of Logopedics and Phoniatrics.