On the Hallucination in Simultaneous Machine Translation
Not on the map. Why?
Abstract (arXiv)
It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information. While many efforts have been made to enhance performance for SiMT, few of them attempt to understand and analyze hallucination in SiMT. Therefore, we conduct a comprehensive analysis of hallucination in SiMT from two perspectives: understanding the distribution of hallucination words and the target-side context usage of them. Intensive experiments demonstrate some valuable findings and particularly show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 11 Jun 2024.
Builds on
23 of 31 references.
References · 23
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
- 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
- 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
- 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
- 2019Bridging the Gap between Training and Inference for Neural Machine Translationcited by 123
- 2019Monotonic Multihead Attentioncited by 91
- 2020Analyzing the Source and Target Contributions to Predictions in Neural Machine Translationcited by 71
- 2019Domain Robustness in Neural Machine Translationcited by 64
- 2020Efficient Wait-k Models for Simultaneous Machine Translationcited by 59
- 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
11 more
- 2020Simultaneous Translation Policies: From Fixed to Adaptivecited by 42
- 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
- 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
- 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
- 2022Modeling Dual Read/Write Paths for Simultaneous Machine Translationcited by 21
- 2020Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderingscited by 20
- 2022Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Frameworkcited by 16
- 2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
- 2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
- 2022Probing Causes of Hallucinations in Neural Machine Translationscited by 3
- 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.