Lune

ACL Findings2021

Better Chinese Sentence Segmentation with Reinforcement Learning

Srivatsan Srinivasan, Chris Dyer

Abstract

A long-standing challenge in Chinese-English machine translation is that sentence boundaries are ambiguous in Chinese orthography, but inferring good splits is necessary for obtaining high quality translations. To solve this, we use reinforcement learning to train a segmentation policy that splits Chinese texts into segments that can be independently translated so as to maximise the overall translation quality. We compare to a variety of segmentation strategies and find that our approach improves the baseline BLEU score on the WMT2020 Chinese-English news translation task by +0.3 BLEU overall and improves the score on input segments that contain more than 60 words by +3 BLEU.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on1

  1. If beam search is the answer, what was the question?Clara Meister, Ryan Cotterell, Tim VieiraEMNLP 2020 · 26 citations

Related papers

  1. Learning Adaptive Segmentation Policy for Simultaneous TranslationRuiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu et al.EMNLP 2020 · 41 citations
  2. Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence SegmentationBenjamin Minixhofer, Jonas Pfeiffer, Ivan VulicACL 2023 · 8 citations
  3. REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASRLiang-Hsuan Tseng, En-Pei Hu, Cheng-Han Chiang, Yuan Tseng et al.NeurIPS 2024 · 5 citations
  4. Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine TranslationBaohao Liao, Yingbo Gao, Hermann NeyEMNLP Findings 2020 · 5 citations
  5. Learning and Analyzing Generation Order for Undirected Sequence ModelsYichen Jiang, Mohit BansalEMNLP Findings 2021 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines