Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding
- URL: http://arxiv.org/abs/2410.15021v1
- Date: Sat, 19 Oct 2024 07:32:10 GMT
- Title: Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding
- Authors: Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe,
- Abstract summary: Minimum Bayes Risk (MBR) decoding can mitigate this problem by utilizing automatic evaluation metrics and model-generated pseudo-references.
We decompose errors in the estimated quality of generated hypotheses into two key factors: bias, which reflects the closeness between utility functions and human evaluations, and diversity, which represents the variation in the estimated quality of utility functions.
- Score: 32.02732402635305
- License:
- Abstract: Text generation commonly relies on greedy and beam decoding that limit the search space and degrade output quality. Minimum Bayes Risk (MBR) decoding can mitigate this problem by utilizing automatic evaluation metrics and model-generated pseudo-references. Previous studies have conducted empirical analyses to reveal the improvement by MBR decoding, and reported various observations. However, despite these observations, the theoretical relationship between them remains uncertain. To address this, we present a novel theoretical interpretation of MBR decoding from the perspective of bias-diversity decomposition. We decompose errors in the estimated quality of generated hypotheses in MBR decoding into two key factors: bias, which reflects the closeness between utility functions and human evaluations, and diversity, which represents the variation in the estimated quality of utility functions. Our theoretical analysis reveals the difficulty in simultaneously improving both bias and diversity, and highlights the effectiveness of increasing diversity to enhance MBR decoding performance. This analysis verifies the alignment between our theoretical insights and the empirical results reported in previous work. Furthermore, to support our theoretical findings, we propose a new metric, pseudo-bias, which approximates the bias term using gold references. We also introduce a new MBR approach, Metric-augmented MBR (MAMBR), which increases diversity by adjusting the behavior of utility functions without altering the pseudo-references. Experimental results across multiple NLP tasks show that the decomposed terms in the bias-diversity decomposition correlate well with performance, and that MAMBR improves text generation quality by modifying utility function behavior. Our code will be available at https://github.com/naist-nlp/mbr-bias-diversity.
Related papers
- On the True Distribution Approximation of Minimum Bayes-Risk Decoding [3.409873726183299]
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation.
Previous studies reported that the performance varies by sampling methods.
This study uses anomaly detection to measure the degree of approximation.
arXiv Detail & Related papers (2024-03-31T17:47:22Z) - Probabilistic Precision and Recall Towards Reliable Evaluation of
Generative Models [7.770029179741429]
We propose P-precision and P-recall (PP&PR), based on a probabilistic approach that address the problems.
We show that our PP&PR provide more reliable estimates for comparing fidelity and diversity than the existing metrics.
arXiv Detail & Related papers (2023-09-04T13:19:17Z) - Towards Multiple References Era -- Addressing Data Leakage and Limited
Reference Diversity in NLG Evaluation [55.92852268168816]
N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks.
Recent studies have revealed a weak correlation between these matching-based metrics and human evaluations.
We propose to utilize textitmultiple references to enhance the consistency between these metrics and human evaluations.
arXiv Detail & Related papers (2023-08-06T14:49:26Z) - A Unified Framework for Multi-distribution Density Ratio Estimation [101.67420298343512]
Binary density ratio estimation (DRE) provides the foundation for many state-of-the-art machine learning algorithms.
We develop a general framework from the perspective of Bregman minimization divergence.
We show that our framework leads to methods that strictly generalize their counterparts in binary DRE.
arXiv Detail & Related papers (2021-12-07T01:23:20Z) - Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma
Distributions [91.63716984911278]
We introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modalities and produces a trustworthy regression result.
Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks.
arXiv Detail & Related papers (2021-11-11T14:28:12Z) - Reenvisioning Collaborative Filtering vs Matrix Factorization [65.74881520196762]
Collaborative filtering models based on matrix factorization and learned similarities using Artificial Neural Networks (ANNs) have gained significant attention in recent years.
Announcement of ANNs within the recommendation ecosystem has been recently questioned, raising several comparisons in terms of efficiency and effectiveness.
We show the potential these techniques may have on beyond-accuracy evaluation while analyzing effect on complementary evaluation dimensions.
arXiv Detail & Related papers (2021-07-28T16:29:38Z) - Understanding the Properties of Minimum Bayes Risk Decoding in Neural
Machine Translation [26.33252528975464]
Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words.
Recent work has tied these shortcomings to beam search.
Eikema & Aziz ( 2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead.
arXiv Detail & Related papers (2021-05-18T13:31:05Z) - Bayesian Uncertainty Estimation of Learned Variational MRI
Reconstruction [63.202627467245584]
We introduce a Bayesian variational framework to quantify the model-immanent (epistemic) uncertainty.
We demonstrate that our approach yields competitive results for undersampled MRI reconstruction.
arXiv Detail & Related papers (2021-02-12T18:08:14Z) - On the Relation between Quality-Diversity Evaluation and
Distribution-Fitting Goal in Text Generation [86.11292297348622]
We show that a linear combination of quality and diversity constitutes a divergence metric between the generated distribution and the real distribution.
We propose CR/NRR as a substitute for quality/diversity metric pair.
arXiv Detail & Related papers (2020-07-03T04:06:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.