A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT

Michael Paul, Eiichiro Sumita, Seiichi Yamamoto

Abstract
This paper proposes a method for integrating example-based and rule-based machine translation systems with statistical methods. It extends a greedy decoder for statistical machine translation (SMT), which searches for an optimal translation by using SMT models starting from a decoder seed, i.e., the source language input paired with an initial translation hypothesis. In order to reduce local optima problems inherent in the search, the outputs generated by multiple translation engines, such as rule-based (RBMT) and example-based (EBMT) systems, are utilized as the initial translation hypotheses. This method outperforms conventional greedy decoding approaches using initial translation hypotheses based on translation examples retrieved from a parallel text corpus. However, the decoding of multiple initial translation hypotheses is computationally expensive. This paper proposes a method to select a single initial translation hypothesis before decoding based on a machine learning approach that judges the appropriateness of multiple initial translation hypotheses and selects the most confident one for decoding. Our approach is evaluated for the translation of dialogues in the travel domain, and the results show that it drastically reduces computational costs without a loss in translation quality.
Anthology ID:
2005.mtsummit-ebmt.15
Volume:
Workshop on example-based machine translation
Month:
September 13-15
Year:
2005
Address:
Phuket, Thailand
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
117–124
Language:
URL:
https://aclanthology.org/2005.mtsummit-ebmt.15
DOI:
Bibkey:
Cite (ACL):
Michael Paul, Eiichiro Sumita, and Seiichi Yamamoto. 2005. A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT. In Workshop on example-based machine translation, pages 117–124, Phuket, Thailand.
Cite (Informal):
A Machine Learning Approach to Hypotheses Selection of Greedy Decoding for SMT (Paul et al., MTSummit 2005)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2005.mtsummit-ebmt.15.pdf
PDF Search