VNU-UET Repository

Exploiting Non-Parallel Corpora for Statistical Machine Translation

Hoang, Cuong and Le, Anh Cuong and Nguyen, Phuong Thai and Ho, Tu Bao (2012) Exploiting Non-Parallel Corpora for Statistical Machine Translation. In: 2012 IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), February 27 - March 1, 2012, Ho Chi Minh city.

Full text not available from this repository.


Constructing a corpus of parallel sentence pairs is an important work in building a Statistical Machine Translation system. It impacts deeply how the quality of a Statistical Machine Translation could achieve. The more parallel sentence pairs we use to train the system, the better translation's quality it is. Nowadays, comparable non-parallel corpora become important resources to alleviate scarcity of parallel corpora. The problem here is how to extract parallel sentence pairs automatically but accurately from comparable non-parallel corpora, which are usually very "noisy". This paper presents how we can apply the reinforcement-learning scheme with our new proposed algorithm for detecting parallel sentence pairs. We specify that from an initial set of parallel sentences in a domain, the proposed model can extract a large number of new parallel sentence pairs from non-parallel corpora resources in different domains, concurrently increasing the system's translation ability gradually.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Electronic publishing;Encyclopedias;Error analysis;Internet;Length measurement;Training;language translation;learning (artificial intelligence);nonparallel corpora;parallel sentence pair detection;reinforcement learning scheme;statistical machine translation system;
Subjects: Information Technology (IT)
?? IT_CS ??
?? IT_GS ??
Divisions: Faculty of Information Technology (FIT)
Depositing User: Prof. Xuan-Tu Tran
Date Deposited: 08 Jan 2013 07:43
Last Modified: 22 May 2015 08:07

Actions (login required)

View Item View Item