Yuan Ding


pdf bib
Better Learning and Decoding for Syntax Based SMT Using PSDIG
Yuan Ding | Martha Palmer
Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers

As an approach to syntax based statistical machine translation (SMT), Probabilistic Synchronous Dependency Insertion Grammars (PSDIG), introduced in (Ding and Palmer, 2005), are a version of synchronous grammars defined on dependency trees. In this paper we discuss better learning and decoding algorithms for a PSDIG MT system. We introduce two new grammar learners: (1) an exhaustive learner combining different heuristics, (2) an n-gram based grammar learner. Combining the grammar rules learned from the two learners improved the performance. We introduce a better decoding algorithm which incorporates a tri-gram language model. According to the Bleu metric, the PSDIG MT system performance is significantly better than IBM Model 4, while on par with the state-of-the-art phrase based system Pharaoh (Koehn, 2004). The improved integration of syntax on both source and target languages opens door to more sophisticated SMT processes.


pdf bib
Machine Translation Using Probabilistic Synchronous Dependency Insertion Grammars
Yuan Ding | Martha Palmer
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05)


pdf bib
Synchronous Dependency Insertion Grammars: A Grammar Formalism for Syntax Based Statistical MT
Yuan Ding | Martha Palmer
Proceedings of the Workshop on Recent Advances in Dependency Grammar


pdf bib
An algorithm for word-level alignment of parallel dependency trees
Yuan Ding | Daniel Gildea | Martha Palmer
Proceedings of Machine Translation Summit IX: Papers

Structural divergence presents a challenge to the use of syntax in statistical machine translation. We address this problem with a new algorithm for alignment of loosely matched non-isomorphic dependency trees. The algorithm selectively relaxes the constraints of the two tree structures while keeping computational complexity polynomial in the length of the sentences. Experimentation with a large Chinese-English corpus shows an improvement in alignment results over the unstructured models of (Brown et al., 1993).


pdf bib
Improving Translation Selection with a New Translation Model Trained by Independent Monolingual Corpora
Ming Zhou | Yuan Ding | Changning Huang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 6, Number 1, February 2001: Special Issue on Natural Language Processing Researches in MSRA