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.
Lineage
Builds on1
Related papers
- Learning Adaptive Segmentation Policy for Simultaneous TranslationRuiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu et al.EMNLP 2020 · 41 citations
- Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence SegmentationBenjamin Minixhofer, Jonas Pfeiffer, Ivan VulicACL 2023 · 8 citations
- 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
- Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine TranslationBaohao Liao, Yingbo Gao, Hermann NeyEMNLP Findings 2020 · 5 citations
- Learning and Analyzing Generation Order for Undirected Sequence ModelsYichen Jiang, Mohit BansalEMNLP Findings 2021 · 1 citation
