Improving Machine Translation Performance by Exploiting Non-Parallel Corpora

By Dragos Stefan Munteanu, Daniel Marcu. 2005

476 citations recorded by the source corpus.

We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performance of a state-of-the-art statistical machine translation system. We also show that a good-quality MT system can be built from scratch by starting with a very small parallel corpus (100,000 words) and exploiting a large non-parallel corpus. Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Graham Neubig
  2. Luke S. Zettlemoyer
  3. Mohit Bansal
  4. Jianfeng Gao
  5. Kyunghyun Cho
  6. Percy Liang
  7. Furu Wei
  8. Noah A. Smith

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Trevor Darrell
  4. Xiaogang Wang
  5. Ming-Hsuan Yang
  6. Andrew Zisserman
  7. Tao Qin
  8. Jitendra Malik

In Natural Language Processing

  1. Holger Schwenk
  2. Graham Neubig
  3. Philipp Koehn
  4. Luke S. Zettlemoyer
  5. Jianfeng Gao
  6. Kyunghyun Cho
  7. Mikel Artetxe
  8. Furu Wei

In Machine Translation

  1. Philipp Koehn
  2. Chenhui Chu
  3. Rudolf Rosa
  4. Ondrej Dusek
  5. Juan Pino
  6. Changhan Wang
  7. Ann Lee
  8. Michal Novák

Citations in the corpus