Expected dependency pair match: predicting translation quality with expected syntactic structure
Autor: | Jeremy G. Kahn, Mari Ostendorf, Matthew Snover |
---|---|
Rok vydání: | 2009 |
Předmět: |
Linguistics and Language
Parsing Dependency (UML) Machine translation business.industry Computer science media_common.quotation_subject computer.software_genre Syntax Language and Linguistics Rule-based machine translation Artificial Intelligence Metric (mathematics) Quality (business) Artificial intelligence Computational linguistics business computer Software Natural language processing media_common |
Zdroj: | Machine Translation. 23:169-179 |
ISSN: | 1573-0573 0922-6567 |
DOI: | 10.1007/s10590-009-9057-6 |
Popis: | Recent efforts to develop new machine translation evaluation methods have tried to account for allowable wording differences either in terms of syntactic structure or synonyms/paraphrases. This paper primarily considers syntactic structure, combining scores from partial syntactic dependency matches with standard local n-gram matches using a statistical parser, and taking advantage of N-best parse probabilities. The new scoring metric, expected dependency pair match (EDPM), is shown to outperform BLEU and TER in terms of correlation to human judgments and as a predictor of HTER. Further, we combine the syntactic features of EDPM with the alternative wording features of TERp, showing a benefit to accounting for syntactic structure on top of semantic equivalency features. |
Databáze: | OpenAIRE |
Externí odkaz: |