Trading Off Diversity and Quality in Natural Language Generation

• URL: http://arxiv.org/abs/2004.10450v1
• Date: Wed, 22 Apr 2020 09:12:10 GMT
• Title: Trading Off Diversity and Quality in Natural Language Generation
• Authors: Hugh Zhang, Daniel Duckworth, Daphne Ippolito, Arvind Neelakantan
• Abstract summary: We cast decoding as a multi-objective optimization problem aiming to simultaneously maximize both response quality and diversity. Our framework enables us to perform the first large-scale evaluation of decoding methods along the entire quality-diversity spectrum. We leverage our findings to create and evaluate an algorithm called emphselective sampling which tractably approximates globally-normalized temperature sampling.
• Score: 12.672685374008259
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For open-ended language generation tasks such as storytelling and dialogue, choosing the right decoding algorithm is critical to controlling the tradeoff between generation quality and diversity. However, there presently exists no consensus on which decoding procedure is best or even the criteria by which to compare them. We address these issues by casting decoding as a multi-objective optimization problem aiming to simultaneously maximize both response quality and diversity. Our framework enables us to perform the first large-scale evaluation of decoding methods along the entire quality-diversity spectrum. We find that when diversity is a priority, all methods perform similarly, but when quality is viewed as more important, the recently proposed nucleus sampling (Holtzman et al. 2019) outperforms all other evaluated decoding algorithms. Our experiments also confirm the existence of the `likelihood trap', the counter-intuitive observation that high likelihood sequences are often surprisingly low quality. We leverage our findings to create and evaluate an algorithm called \emph{selective sampling} which tractably approximates globally-normalized temperature sampling.

Related papers

• Illuminating the Diversity-Fitness Trade-Off in Black-Box Optimization [9.838618121102053]
  In real-world applications, users often favor structurally diverse design choices over one high-quality solution. This paper presents a fresh perspective on this challenge by considering the problem of identifying a fixed number of solutions with a pairwise distance above a specified threshold.
  arXiv  Detail & Related papers  (2024-08-29T09:55:55Z)
• Batch Bayesian Optimization for Replicable Experimental Design [56.64902148159355]
  Many real-world design problems evaluate multiple experimental conditions in parallel and replicate each condition multiple times due to large and heteroscedastic observation noise. We propose the Batch Thompson Sampling for Replicable Experimental Design framework, which encompasses three algorithms. We show the effectiveness of our algorithms in two practical real-world applications: precision agriculture and AutoML.
  arXiv  Detail & Related papers  (2023-11-02T12:46:03Z)
• Best-$k$ Search Algorithm for Neural Text Generation [118.02691398555781]
  We propose a deterministic search algorithm balancing both quality and diversity. The proposed algorithm is parameter-free, lightweight, efficient, and easy to use.
  arXiv  Detail & Related papers  (2022-11-22T00:26:13Z)
• Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding [27.454582992694974]
  We present crowd sampling, a family of decoding methods based on Bayesian risk minimization. Crowd sampling seeks to select a candidate from a pool of candidates that has the least expected risk. Experiments show that crowd sampling delivers improvements of 3-7 ROUGE and BLEU points across a wide range of tasks.
  arXiv  Detail & Related papers  (2022-11-14T18:57:37Z)
• An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generation [77.44921096644698]
  We present a systematic analysis of the impact of decoding algorithms on LM fairness. We analyze the trade-off between fairness, diversity and quality.
  arXiv  Detail & Related papers  (2022-10-07T21:33:34Z)
• Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms [1.827510863075184]
  We introduce Relevance-guided Unsupervised Discovery of Abilities; a Quality-Diversity algorithm that autonomously finds a behavioural characterisation tailored to the task at hand. We evaluate our approach on a simulated robotic environment, where the robot has to autonomously discover its abilities based on its full sensory data.
  arXiv  Detail & Related papers  (2022-04-21T00:29:38Z)
• On Decoding Strategies for Neural Text Generators [73.48162198041884]
  We study the interaction between language generation tasks and decoding strategies. We measure changes in attributes of generated text as a function of both decoding strategy and task. Our results reveal both previously-observed and surprising findings.
  arXiv  Detail & Related papers  (2022-03-29T16:25:30Z)
• Determinantal Beam Search [75.84501052642361]
  Beam search is a go-to strategy for decoding neural sequence models. In use-cases that call for multiple solutions, a diverse or representative set is often desired. By posing iterations in beam search as a series of subdeterminant problems, we can turn the algorithm into a diverse subset selection process.
  arXiv  Detail & Related papers  (2021-06-14T13:01:46Z)
• Quality-Diversity Optimization: a novel branch of stochastic optimization [5.677685109155078]
  Multimodal optimization algorithms search for the highest peaks in the search space that can be more than one. Quality-Diversity algorithms are a recent addition to the evolutionary computation toolbox that do not only search for a single set of local optima, but instead try to illuminate the search space.
  arXiv  Detail & Related papers  (2020-12-08T09:52:50Z)
• Consistency of a Recurrent Language Model With Respect to Incomplete Decoding [67.54760086239514]
  We study the issue of receiving infinite-length sequences from a recurrent language model. We propose two remedies which address inconsistency: consistent variants of top-k and nucleus sampling, and a self-terminating recurrent language model.
  arXiv  Detail & Related papers  (2020-02-06T19:56:15Z)

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.