Zhuofan Wen, Shangtong Gui, Yang Feng. Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration. The Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS 2024), 0-1
Langlin Huang, Yang Feng. Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation. The 62nd Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2024), August 11-16, 2024, 9794–9801, Bangkok, Thailand, pdf
Mengyu Bu, Shuhao Gu, Yang Feng. Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features. The 62nd Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2024), August 11-16, 2024, 10410–10423, Bangkok, Thailand, pdf
Tian Yu, Shaolei Zhang, Yang Feng. Truth-Aware Context Selection: Mitigating the Hallucinations of Large Language Models Being Misled by Untruthful Contexts. The 62nd Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2024), August 11-16, 2024, 10862–10884, Bangkok, Thailand, pdf
Qingkai Fang, Zhengrui Ma, Yan Zhou, Min Zhang, Yang Feng. CTC-based Non-autoregressive Textless Speech-to-Speech Translation. The 62nd Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2024), August 11-16, 2024, 9155–9161, Bangkok, Thailand, pdf
Shoutao Guo, Shaolei Zhang, Yang Feng. Decoder-only Streaming Transformer for Simultaneous Translation. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11-16, 2024, 8851–8864, Bangkok, Thailand, pdf
Shaolei Zhang, Tian Yu, Yang Feng. TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11-16, 2024, 8908–8949, Bangkok, Thailand, pdf
Shaolei Zhang, Qingkai Fang, Shoutao Guo, Zhengrui Ma, Min Zhang, Yang Feng. StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11-16, 2024, 8964–8986, Bangkok, Thailand, pdf
Qingkai Fang, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng. Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data? The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11-16, 2024, 7264–7277, Bangkok, Thailand, pdf
Zhengrui Ma, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Min Zhang. A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation. The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), August 11-16, 2024, 1557–1575, Bangkok, Thailand, pdf
Zhengrui Ma, Shaolei Zhang, Shoutao Guo, Chenze Shao, Min Zhang, Yang Feng. Non-autoregressive Streaming Transformer for Simultaneous Translation. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), December 6-10, 2023, 5177-5190, Singapore, pdf
Wenyu Guo, Qingkai Fang, Dong Yu, Yang Feng. Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), December 6-10, 2023, 2863-2874, Singapore, pdf
Zhuocheng Zhang, Shuhao Gu, Min zhang, Yang Feng. Scaling Law for Document-Level Neural Machine Translation. The 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), December 6-10, 2023, 8290-8303, Singapore, pdf
Zhuocheng Zhang*, Shuhao Gu*, Min zhang, Yang Feng (*: 共同一作). Addressing the Length Bias Challenge in Document-Level Neural Machine Translation. The 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), December 6-10, 2023, 11545-11556, Singapore, pdf
Langlin Huang, Shuhao Gu, Zhuocheng Zhang, Yang Feng*. Enhancing Neural Machine Translation with Semantic Units. The 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), December 6-10, 2023, 2264-2277, Singapore, pdf
Shoutao Guo, Shaolei Zhang, Yang Feng. Simultaneous Machine Translation with Tailored Reference. The 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), December 6-10, 2023, 3070-3084, Singapore, pdf
Shaolei Zhang, Yang Feng. Unified Segment-to-Segment Framework for Simultaneous Sequence Generation. The Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), December 10-16, 2023, 45235-45258, New Orleans, USA, pdf
Qingkai Fang, Yan Zhou, Yang Feng. DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation. The Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), December 10-16, 2023, 72604-72623, New Orleans, USA, pdf
Chenze Shao*, Zhengrui Ma*, Min Zhang, Yang Feng (*: 共同一作). Beyond MLE: Convex Loss for Text Generation. The Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), December 10-16, 2023, 8913-8936, New Orleans, USA, pdf
Shangtong Gui, Chenze Shao, Zhengrui Ma, Xishan Zhang, Yunji Chen, Yang Feng. Non-autoregressive Machine Translation with Probabilistic Context-free Grammar. The Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), December 10-16, 2023, 5598-5615, New Orleans, USA, pdf
Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang, Zhengrui Ma, Yan Zhou, Langlin Huang, Mengyu Bu, Shangtong Gui, Yunji Chen, Xilin Chen, Yang Feng. BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models. arXiv, June 21, 2023, pdf
Qingkai Fang, Yang Feng. Understanding and Bridging the Modality Gap for Speech Translation. The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), July 9-14, 2023, 15864-15881, Toronto, Canada, pdf
Qingkai Fang, Yang Feng. Back Translation for Speech-to-text Translation Without Transcripts. The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), July 9-14, 2023, 4567–4587, Toronto, Canada, pdf
Shoutao Guo, Shaolei Zhang, Yang Feng. Learning Optimal Policy for Simultaneous Machine Translationvia Binary Search. The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), July 9-14, 2023, 2318–2333, Toronto, Canada, pdf
Yan Zhou, Qingkai Fang, Yang Feng. CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation. The 61th Annual Meeting of the Association for Computational Linguistics (ACL 2023), July 9-14, 2023, 7873–7887, Toronto, Canada, pdf
Shaolei Zhang, Yang Feng. End-to-End Simultaneous Speech Translation with Differentiable Segmentation. The 61th Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2023),July 9-14, 2023, 7659–7680, Toronto, Canada, pdf
Zhengrui Ma, Chenze Shao, Shangtong Gui, Min Zhang and Yang Feng. Fuzzy Alignments in Directed Acyclic Graph for Non-autoregressive Machine Translation. The 11th International Conference on Learning Representations (ICLR 2023), May 1-5, 2023, Kigali, Rwanda, pdf
Qingkai Fang, Rong Ye, Lei Li, Yang Feng, Mingxuan Wang. STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 7050–7062, online, pdf
Qingkai Fang, Yang Feng. Neural Machine Translation with Phrase-Level Universal Visual Representations. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 5687–5698, online, pdf
Shaolei Zhang, Yang Feng. Gaussian Multi-head Attention for Simultaneous Machine Translation. The 60th Annual Meeting of the Association for Computational Linguistics (Findings of ACL-2022), May 22-27, 2022, 3019–3030, online, pdf
Chenze Shao, Xuanfu Wu, Yang Feng. One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation. 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL-HLT 2022), July 10–15, 2022, 3779–3791, online pdf
Shaolei Zhang, Yang Feng. Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 6775–6788, online, pdf
Shaolei Zhang, Yang Feng. Modeling Dual Read/Write Paths for Simultaneous Machine Translation. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 2461–2477, online, pdf
Dengji Guo, Zhengrui Ma, Min Zhang, Yang Feng. Prediction Difference Regularization against Perturbation for Neural Machine Translation. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 7665–7675, online, pdf
Chenze Shao, Yang Feng. Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation. The 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), May 22-27, 2022, 2023–2036, online, pdf
Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu. Relational Surrogate Loss Learning. The Tenth International Conference on Learning Representations (ICLR-2022), Apr 25-29, 2022, online, pdf
Shoutao Guo, Shaolei Zhang, Yang Feng. Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation. The 2022 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2022), December 7 – 11, 2022, 2264–2278, online & offline pdf
Shaolei Zhang, Shoutao Guo, Yang Feng. Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation. The 2022 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2022), December 7 – 11, 2022, 2249–2263, online & offline pdf
Chenze Shao, Zhengrui Ma, Yang Feng. Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation. The 2022 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2022), December 7 – 11, 2022, 4390–4397, online & offline pdf
Shuhao Gu, Yang Feng. Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings. The 2022 Conference on Empirical Methods in Natural Language Processing(Findings of EMNLP 2022), December 7 – 11, 2022, 6492–6504, online & offline pdf
Zhe Yang, Qingkai Fang, Yang Feng. Low-resource Neural Machine Translation with Cross-modal Alignment. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), December 7 – 11, 2022, 10134–10146, online & offline pdf
Shaolei Zhang, Yang Feng. Information-Transport-based Policy for Simultaneous Translation. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), December 7 – 11, 2022, 992–1013, online & offline pdf
Shuhao Gu, Bojie Hu, Yang Feng. Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), December 7 – 11, 2022, 1707-1718, online & offline pdf