Learning Natural Language Generation with Truncated Reinforcement Learning

Alice Martin; Guillaume Quispe; Charles Ollion; Sylvain Le Corff; Florian Strub; Olivier Pietquin

doi:10.18653/v1/2022.naacl-main.2

ScienceGate Book Chapters

JOURNAL ARTICLE

Learning Natural Language Generation with Truncated Reinforcement Learning

Alice Martin Guillaume Quispe Charles Ollion Sylvain Le Corff Florian Strub Olivier Pietquin

Year: 2022 Journal: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Pages: 12-37

DOI: 10.18653/v1/2022.naacl-main.2

Get Full-Text PDF Get Analytical Report

Abstract

Alice Martin, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Keywords:

Computer science Alice (programming language) Natural language Reinforcement learning Computational linguistics Artificial intelligence Language acquisition Linguistics Natural language processing Language technology Cognitive science Programming language Psychology Comprehension approach Philosophy

Metrics

Cited By

0.59

FWCI (Field Weighted Citation Impact)

Refs

0.63

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Natural Language Processing Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Learning Natural Language Generation with Truncated Reinforcement Learning

Abstract

Metrics

Citation History

Topics

Related Documents

Natural Language Generation (NLG) with Reinforcement Learning (RL)

Hierarchical reinforcement learning for situated natural language generation

A Reinforcement Learning Approach for Abductive Natural Language Generation

Inverse Reinforcement Learning with Natural Language Goals

Using reinforcement learning with external rewards for open-domain natural language generation