Discourse Structure in Machine Translation Evaluation
| Autor: | Preslav Nakov, Francisco Guzmán, Lluís Màrquez, Shafiq Joty |
|---|---|
| Přispěvatelé: | School of Computer Science and Engineering |
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Machine Translation Evaluation Linguistics and Language Machine translation Computer science 68T50 02 engineering and technology computer.software_genre Language and Linguistics Computer Aided Language Translation Artificial Intelligence Simple (abstract algebra) Similarity (psychology) 0202 electrical engineering electronic engineering information engineering Relevance (information retrieval) Engineering::Computer science and engineering [DRNTU] 060201 languages & linguistics Computer Science - Computation and Language Parsing business.industry I.2.7 06 humanities and the arts Computer Science Applications Tree (data structure) Rhetorical Structure Theory 0602 languages and literature Metric (mathematics) 020201 artificial intelligence & image processing Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing |
| Zdroj: | Computational Linguistics. 43:683-722 |
| ISSN: | 1530-9312 0891-2017 |
| Popis: | In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment- and at the system-level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular we show that: (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference tree is positively correlated with translation quality. machine translation, machine translation evaluation, discourse analysis. Computational Linguistics, 2017 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|