paper-with-me

Papers

Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport

2025-05-29 · Yuu Jinnai

Document-level text generation tasks are known to be more difficult than sentence-level text generation tasks as they require the understanding of longer context to generate high-quality texts. In this paper, we investigate the adaption of Minimum Bayes Risk (MBR) decoding for document-level text generation tasks. MBR decoding makes use of a utility function to estimate the output with the highest expected utility from a set of candidate outputs. Although MBR decoding is shown to be effective in a wide range of sentence-level text generation tasks, its performance on document-level text generation tasks is limited as many of the utility functions are designed for evaluating the utility of sentences. To this end, we propose MBR-OT, a variant of MBR decoding using Wasserstein distance to compute the utility of a document using a sentence-level utility function. The experimental result shows that the performance of MBR-OT outperforms that of the standard MBR in document-level machine translation, text simplification, and dense image captioning tasks. Our code is available at https://github.com/jinnaiyuu/mbr-optimal-transport

📄 PDF Abstract BibTeX arXiv:2505.23078

Code (1)

jinnaiyuu/mbr-optimal-transport 공식 구현 pytorch

Tasks

Document Level Machine TranslationImage CaptioningMachine TranslationSentenceText GenerationText Simplification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers

2022-12-07 · Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney

Recently, RNN-Transducers have achieved remarkable results on various automatic speech recognition tasks. However, lattice-free sequence discriminative training methods, which obtain superior performance in hybrid models…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models

2023-11-13 · Junpeng Li, Zixia Jia, Zilong Zheng

Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representa…

Document-level Relation ExtractionIn-Context LearningLanguage ModelingLanguage Modelling+4

BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering

2026-04-24 · Jinghong Chen, Jingbiao Mei, Guangyu Yang, Bill Byrne arxiv

A common approach to question answering with retrieval-augmented generation (RAG) is to concatenate documents into a single context and pass it to a language model to generate an answer. While simple, this strategy can o…

Visual Question Answering

Improving Minimum Bayes Risk Decoding with Multi-Prompt

2024-07-22 · David Heineman, Yao Dou, Wei Xu

While instruction fine-tuned LLMs are effective text generators, sensitivity to prompt construction makes performance unstable and sub-optimal in practice. Relying on a single "best" prompt cannot capture all differing a…

Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognition

2025-10-22 · Yuu Jinnai arxiv

Recent work has shown that sample-based Minimum Bayes Risk (MBR) decoding outperforms beam search in text-to-text generation tasks, such as machine translation, text summarization, and image captioning. On the other hand…

Machine TranslationText SummarizationSpeech RecognitionImage Captioning