paper-with-me

홈 › Papers

On the True Distribution Approximation of Minimum Bayes-Risk Decoding

2024-03-31 · Atsumoto Ohashi, Ukyo Honda, Tetsuro Morimura, Yuu Jinnai

Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods. From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of references. However, this approximation has not been the subject of in-depth study. In this study, we propose using anomaly detection to measure the degree of approximation. We first closely examine the performance variation and then show that previous hypotheses about samples do not correlate well with the variation, but our introduced anomaly scores do. The results are the first to empirically support the link between the performance and the core assumption of MBR decoding.

📄 PDF Abstract BibTeX arXiv:2404.00752

Code (1)

cyberagentailab/mbr-anomaly 공식 구현 pytorch

Tasks

Anomaly DetectionText Generation

Similar Papers 제목 키워드 기반

Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation

2021-08-10 · Bryan Eikema, Wilker Aziz

In NMT we search for the mode of the model distribution to form predictions. The mode and other high-probability translations found by beam search have been shown to often be inadequate in a number of ways. This prevents…

Machine TranslationNMTTranslation

$α$-Variational Inference with Statistical Guarantees

2017-10-09 · Yun Yang, Debdeep Pati, Anirban Bhattacharya

We propose a family of variational approximations to Bayesian posterior distributions, called $\alpha$-VB, with provable statistical guarantees. The standard variational approximation is a special case of $\alpha$-VB wit…

Variational Inference

Model-Based Minimum Bayes Risk Decoding for Text Generation

2023-11-09 · Yuu Jinnai, Tetsuro Morimura, Ukyo Honda, Kaito Ariu 외

Minimum Bayes Risk (MBR) decoding has been shown to be a powerful alternative to beam search decoding in a variety of text generation tasks. MBR decoding selects a hypothesis from a pool of hypotheses that has the least …

DecoderText Generation

Variational Bayes Inference in Digital Receivers

2018-11-03 · Viet Hung Tran

The digital telecommunications receiver is an important context for inference methodology, the key objective being to minimize the expected loss function in recovering the transmitted information. For that criterion, the…

LEMMA

Moments and Root-Mean-Square Error of the Bayesian MMSE Estimator of Classification Error in the Gaussian Model

2013-10-05 · Amin Zollanvari, Edward R. Dougherty

The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifi…

General Classification