Work

Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings

Year: 2016
Type: conference-paper
Abstract: The phrase table is considered to be the main bilingual resource for the phrase-based statistical machine translation (PBSMT) model. During translation, a source sentence is decomposed\ninto several phrases. The best match of each source phrase is selected among several target-side\ncounterparts within the phrase table, and processed by the decoder to generate a sentence-level\ntranslation. The best match is chosen according to several factors, including a set of bilingual\nfeatures. PBSMT engines by default provide four probability scores in phrase tables which are\nconsidered as the main set of bilingual features. Our goal is to enrich that set of features, as a\nbetter feature set should yield better translations. We propose new scores generated by a Convolutional Neural Network (CNN) which indicate the semantic relatedness of phrase pairs. We\nevaluate our model in different experimental settings with different language pairs. We observe\nsignificant improvements when the proposed features are incorporated into the PBSMT pipeline.
Language: English
Open Access status: green
OpenAlex ID: W2578511464
FWCI: 0.506
Cites: 25
Cited by: 7
Related to: 10