Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models
Sumanta Bhattacharyya, Amirmohammad Rooshenas, Subhajit Naskar, Simeng Sun, Mohit Iyyer, Andrew McCallum
2021年份
21顶会引用
摘要
The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper21
- SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive SummarizationMathieu Ravaut, Shafiq R. Joty, Nancy F. ChenACL 2022 · 被引用 116 次
- On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic ForgettingTomasz Korbak, Hady Elsahar, Germán Kruszewski, Marc DymetmanNeurIPS 2022 · 被引用 98 次
- Energy-Based Transformers are Scalable Learners and ThinkersAlexi Gladstone, Ganesh Nanduru, Md Mofijul Islam, Peixuan Han 等ICLR 2026 · 被引用 38 次
- CoNT: Contrastive Neural Text GenerationChenxin An, Jiangtao Feng, Kai Lv, Lingpeng Kong 等NeurIPS 2022 · 被引用 37 次
- LENS: A Learnable Evaluation Metric for Text SimplificationMounica Maddela, Yao Dou, David Heineman, Wei XuACL 2023 · 被引用 21 次
它引用的顶会 Paper5
- Incorporating BERT into Neural Machine TranslationJinhua Zhu, Yingce Xia, Lijun Wu, Di He 等ICLR 2020 · 被引用 391 次
- Masked Language Model ScoringJulian Salazar, Davis Liang, Toan Q. Nguyen, Katrin KirchhoffACL 2020 · 被引用 167 次
- Residual Energy-Based Models for Text GenerationYuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam 等ICLR 2020 · 被引用 147 次
- On the Weaknesses of Reinforcement Learning for Neural Machine TranslationLeshem Choshen, Lior Fox, Zohar Aizenbud, Omri AbendICLR 2020 · 被引用 124 次
- Incorporating BERT into Parallel Sequence Decoding with AdaptersJunliang Guo, Zhirui Zhang, Linli Xu, Hao-Ran Wei 等NeurIPS 2020 · 被引用 72 次
相关 Paper
- Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine TranslationChenze Shao, Jinchao Zhang, Yang Feng, Fandong Meng 等AAAI 2020 · 被引用 95 次
- Sentence-level Aggregation of Lexical Metrics Correlates Stronger with Human Judgements than Corpus-level AggregationPaulo R. Cavalin, Pedro Henrique Domingues, Claudio S. PinhanezAAAI 2025 · 被引用 5 次
- Machine Translation Decoding beyond Beam SearchRémi Leblond, Jean-Baptiste Alayrac, Laurent Sifre, Miruna Pislar 等EMNLP 2021 · 被引用 6 次
- Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 PapersBenjamin Marie, Atsushi Fujita, Raphael RubinoACL 2021
- Aligned Cross Entropy for Non-Autoregressive Machine TranslationMarjan Ghazvininejad, Vladimir Karpukhin, Luke Zettlemoyer, Omer LevyICML 2020 · 被引用 121 次
