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.
Authors: Peyman Passban, Qun Liu, Andy Way
Institution: Dublin City University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Science Foundation Ireland
OpenAlex ID: W2578511464
