Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
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
Code (1)
Tasks
Document Level Machine TranslationImage CaptioningMachine TranslationSentenceText GenerationText SimplificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
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 RecognitionSemi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models
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+4BERAG: Bayesian Ensemble Retrieval-Augmented Generation for Knowledge-based Visual Question Answering
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 AnsweringImproving Minimum Bayes Risk Decoding with Multi-Prompt
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
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