Which Discriminator for Cooperative Text Generation? - Sorbonne Université
Conference Papers Year : 2022

Which Discriminator for Cooperative Text Generation?

Abstract

Language models generate texts by successively predicting probability distributions for next tokens given past ones. A growing field of interest tries to leverage external information in the decoding process so that the generated texts have desired properties, such as being more natural, non toxic, faithful, or having a specific writing style. A solution is to use a classifier at each generation step, resulting in a cooperative environment where the classifier guides the decoding of the language model distribution towards relevant texts for the task at hand. In this paper, we examine three families of (transformer-based) discriminators for this specific task of cooperative decoding: bidirectional, left-to-right and generative ones. We evaluate the pros and cons of these different types of discriminators for cooperative generation, exploring respective accuracy on classification tasks along with their impact on the resulting sample quality and computational performances. We also provide the code of a batched implementation of the powerful cooperative decoding strategy used for our experiments, the Monte Carlo Tree Search, working with each discriminator for Natural Language Generation.
Fichier principal
Vignette du fichier
Which_discrim_arXiv.pdf (749.34 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03718429 , version 1 (21-10-2022)

Licence

Identifiers

Cite

Antoine Chaffin, Thomas Scialom, Sylvain Lamprier, Jacopo Staiano, Benjamin Piwowarski, et al.. Which Discriminator for Cooperative Text Generation?. SIGIR 2022 - 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2022, Madrid, Spain. pp.2360-2365, ⟨10.1145/3477495.3531858⟩. ⟨hal-03718429⟩
119 View
93 Download

Altmetric

Share

More