EMNLP Findings2022
Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation
Abstract
Simultaneous machine translation (SiMT) outputs the translation while receiving the source inputs, and hence needs to balance the received source information and translated target information to make a reasonable decision between waiting for inputs or outputting translation. Previous methods always balance source and target information at the token level, either directly waiting for a fixed number of tokens or adjusting the waiting based on the current token. In this paper, we propose a Wait-info Policy to balance source and target at the information level. We first quantify the amount of information contained in each token, named info. Then during simultaneous translation, the decision of waiting or outputting is made based on the comparison results between the total info of previous target outputs and received source inputs. Experiments show that our method outperforms strong baselines under and achieves better balance via the proposed info 1 .
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.
9 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Hidden Markov Transformer for Simultaneous Machine Translation cites Monotonic Multihead Attention
- Hidden Markov Transformer for Simultaneous Machine Translation cites Future-Guided Incremental Transformer for Simultaneous Translation
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation cites Hidden Markov Transformer for Simultaneous Machine Translation
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation cites Learning Optimal Policy for Simultaneous Machine Translation via Binary Search
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation cites Monotonic Multihead Attention
- Unified Segment-to-Segment Framework for Simultaneous Sequence Generation cites Future-Guided Incremental Transformer for Simultaneous Translation
- Learning Optimal Policy for Simultaneous Machine Translation via Binary Search cites Monotonic Multihead Attention
- Learning Optimal Policy for Simultaneous Machine Translation via Binary Search cites Future-Guided Incremental Transformer for Simultaneous Translation
- Learning Optimal Policy for Simultaneous Machine Translation via Binary Search cites Learning Adaptive Segmentation Policy for Simultaneous Translation
- Future-Guided Incremental Transformer for Simultaneous Translation cites Monotonic Multihead Attention
- Decoder-only Streaming Transformer for Simultaneous Translation cites Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
- Decoder-only Streaming Transformer for Simultaneous Translation cites Learning Optimal Policy for Simultaneous Machine Translation via Binary Search
- Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation cites Hidden Markov Transformer for Simultaneous Machine Translation
- Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation cites Learning Optimal Policy for Simultaneous Machine Translation via Binary Search
- Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation cites Monotonic Multihead Attention
- Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation cites Decoder-only Streaming Transformer for Simultaneous Translation
- Learning Adaptive Segmentation Policy for Simultaneous Translation cites Monotonic Multihead Attention
Cited by top-tier papers9
- Hidden Markov Transformer for Simultaneous Machine TranslationShaolei Zhang, Yang FengICLR 2023 · 11 citations
- Unified Segment-to-Segment Framework for Simultaneous Sequence GenerationShaolei Zhang, Yang FengNeurIPS 2023 · 9 citations
- Learning Optimal Policy for Simultaneous Machine Translation via Binary SearchShoutao Guo, Shaolei Zhang, Yang FengACL 2023 · 9 citations
- Decoder-only Streaming Transformer for Simultaneous TranslationShoutao Guo, Shaolei Zhang, Yang FengACL 2024 · 3 citations
- Large Language Models Are Read/Write Policy-Makers for Simultaneous GenerationShoutao Guo, Shaolei Zhang, Zhengrui Ma, Yang FengAAAI 2025 · 3 citations
Builds on13
- Monotonic Multihead AttentionXutai Ma, Juan Miguel Pino, James Cross, Liezl Puzon et al.ICLR 2020 · 148 citations
- Attention is Not Only a Weight: Analyzing Transformers with Vector NormsGoro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro InuiEMNLP 2020 · 138 citations
- Norm-Based Curriculum Learning for Neural Machine TranslationXuebo Liu, Houtim Lai, Derek F. Wong, Lidia S. ChaoACL 2020 · 97 citations
- Future-Guided Incremental Transformer for Simultaneous TranslationShaolei Zhang, Yang Feng, Liangyou LiAAAI 2021 · 44 citations
- Learning Adaptive Segmentation Policy for Simultaneous TranslationRuiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu et al.EMNLP 2020 · 41 citations
Related papers
- Information-Transport-based Policy for Simultaneous TranslationShaolei Zhang, Yang FengEMNLP 2022 · 25 citations
- Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k PolicyShaolei Zhang, Yang FengEMNLP 2021 · 19 citations
- Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine TranslationShoutao Guo, Shaolei Zhang, Yang FengEMNLP Findings 2022 · 10 citations
- Modeling Dual Read/Write Paths for Simultaneous Machine TranslationShaolei Zhang, Yang FengACL 2022 · 27 citations
- Gaussian Multi-head Attention for Simultaneous Machine TranslationShaolei Zhang, Yang FengACL Findings 2022 · 15 citations
