Year: 2021
Type: preprint
Abstract: Document-level machine translation conditions on surrounding sentences to produce coherent translations. There has been much recent work in this area with the introduction of custom model architectures and decoding algorithms. This paper presents a systematic comparison of selected approaches from the literature on two benchmarks for which document-level phenomena evaluation suites exist. We find that a simple method based purely on back-translating monolingual document-level data performs as well as much more elaborate alternatives, both in terms of document-level metrics as well as human evaluation.
Source: arXiv (Cornell University)
Authors: Ma, Zhiyi, Edunov, Sergey, Auli, Michael
Institutions: Meta (United States), Meta (United Kingdom)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3122354723