Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 21-33
Abstract
Rico Sennrich, Jannis Vamvas, Alireza Mohammadshahi. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers). 2024.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Hallucinations in Large Multilingual Translation ModelsTransactions of the Association for Computational Linguistics, 2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural MetricsTransactions of the Association for Computational Linguistics, 2022
- The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine TranslationTransactions of the Association for Computational Linguistics, 2022
- SimCSE: Simple Contrastive Learning of Sentence Embeddings2021
- Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation2021
- Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation2020
- Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationTransactions of the Association for Computational Linguistics, 2017
- Grounded Compositional Semantics for Finding and Describing Images with SentencesTransactions of the Association for Computational Linguistics, 2014
- Dimensionality Reduction by Learning an Invariant Mapping2006