Meaning preservation in Example-based Machine Translation with structural semantics

• Published in: Expert systems with applications Vol. 78; pp. 242 - 258
• Main Authors: Chua, Chong Chai, Lim, Tek Yong, Soon, Lay-Ki, Tang, Enya Kong, Ranaivo-Malançon, Bali
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.07.2017; Elsevier BV
• Subjects: Decomposition; Example-based Machine Translation; Grammar; Machine translation; Preservation; Semantic roles; Semantics; Structural semantics; Structured String-Tree Correspondence; Synchronous Structured String-Tree Correspondence; Translations; Synchronous Structured String-Tree Correspondence; Structural semantics; Semantic roles; Example-based Machine Translation; Structured String-Tree Correspondence
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2017.02.021

•Introduce Structural Semantic Annotation to improve English to Malay EBMT System.•Emphasize meaning structure preservation in the automated translation process.•Translation examples representation is extended with Structural Semantic Annotation.•Resolved the fragmentation and inconsistency issues in EBMT system.•The result of the English to Malay automated translation is improved. The main tasks in Example-based Machine Translation (EBMT) comprise of source text decomposition, following with translation examples matching and selection, and finally adaptation and recombination of the target translation. As the natural language is ambiguous in nature, the preservation of source text’s meaning throughout these processes is complex and challenging. A structural semantics is introduced, as an attempt towards meaning-based approach to improve the EBMT system. The structural semantics is used to support deeper semantic similarity measurement and impose structural constraints in translation examples selection. A semantic compositional structure is derived from the structural semantics of the selected translation examples. This semantic compositional structure serves as a representation structure to preserve the consistency and integrity of the input sentence’s meaning structure throughout the recombination process. In this paper, an English to Malay EBMT system is presented to demonstrate the practical application of this structural semantics. Evaluation of the translation test results shows that the new translation framework based on the structural semantics has outperformed the previous EBMT framework.