A Comparison of Approaches to Document-level Machine Translation

2021/01/26 by Zhiyi Ma, Sergey Edunov, Ma, Zhiyi +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2101.11040

openalex publication_date 2021/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Pointer Sentinel Mixture Models
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• The Neural Noisy Channel
• Exploiting Cross-Sentence Context for Neural Machine Translation
• fairseq: A Fast, Extensible Toolkit for Sequence Modeling
• Layer Normalization

Related

• Document-Level Language Models for Machine Translation
• Automatic Evaluation Metrics for Document-level Translation: Overview, Challenges and Trends
• Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
• Escaping the sentence-level paradigm in machine translation
• Rethinking Document-level Neural Machine Translation