paper-with-me

홈 › Papers

Faster Minimum Bayes Risk Decoding with Confidence-based Pruning

2023-11-25 · Julius Cheng, Andreas Vlachos

Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic evaluations. However, the standard sampling-based algorithm for MBR is substantially more computationally expensive than beam search, requiring a large number of samples as well as a quadratic number of calls to the utility function, limiting its applicability. We describe an algorithm for MBR which gradually grows the number of samples used to estimate the utility while pruning hypotheses that are unlikely to have the highest utility according to confidence estimates obtained with bootstrap sampling. Our method requires fewer samples and drastically reduces the number of calls to the utility function compared to standard MBR while being statistically indistinguishable in terms of accuracy. We demonstrate the effectiveness of our approach in experiments on three language pairs, using chrF++ and COMET as utility/evaluation metrics.

📄 PDF Abstract BibTeX arXiv:2311.14919

Code (1)

juliusc/pruning_mbr 공식 구현

Tasks

Machine TranslationText Generation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

2024-01-05 · Yuu Jinnai, Kaito Ariu

Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of time for inference to compute the MBR obje…

Image CaptioningMachine TranslationText GenerationText Summarization+1

Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition

2026-06-16 · Hiroyuki Deguchi, Takatomo Kano, Katsuki Chousa, Marc Delcroix arxiv

Non-autoregressive (NAR) decoding generates output tokens in parallel, making speech recognition faster than autoregressive decoding, which generates them sequentially from left to right. However, the recognition perform…

Speech Recognition

Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation

2017-04-11 · Raphael Shu, Hideki Nakayama

For extended periods of time, sequence generation models rely on beam search algorithm to generate output sequence. However, the correctness of beam search degrades when the a model is over-confident about a suboptimal p…

GPUMachine TranslationRerankingTranslation

Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding

2023-11-14 · Guangyu Yang, Jinghong Chen, Weizhe Lin, Bill Byrne

Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Re…

Machine TranslationNMTreinforcement-learningReinforcement Learning+2

Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistency

2025-02-07 · Roman Vashurin, Maiya Goloburda, Albina Ilina, Alexander Rubashevskii 외

Uncertainty quantification (UQ) methods for Large Language Models (LLMs) encompass a variety of approaches, with two major types being particularly prominent: information-based, which focus on model confidence expressed …

Abstractive Text SummarizationMachine TranslationQuestion AnsweringUncertainty Quantification