Work

Multi-Source Neural Translation

Year: 2016

Type: conference-paper

Abstract: We build a multi-source machine translation model and train it to maximize the probability of a target English string given French and German sources.Using the neural encoderdecoder framework, we explore several combination methods and report up to +4.8 Bleu increases on top of a very strong attentionbased neural translation model.

Source: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)

DOI: 10.18653/v1/n16-1004

Authors: Barret Zoph, Kevin Knight

Institution: University of Southern California

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Defense Advanced Research Projects Agency, Army Research Office

Awards: G7452299184, G8092615179