@inproceedings{martin-etal-2022-learning,
title = "Learning Natural Language Generation with Truncated Reinforcement Learning",
author = "Martin, Alice and
Quispe, Guillaume and
Ollion, Charles and
Le Corff, Sylvain and
Strub, Florian and
Pietquin, Olivier",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.2",
doi = "10.18653/v1/2022.naacl-main.2",
pages = "12--37",
abstract = "This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original approach to train conditional languagemodels without a supervised learning phase, by only using reinforcement learning (RL). As RL methods unsuccessfully scale to large action spaces, we dynamically truncate the vocabulary space using a generic language model. TrufLL thus enables to train a language agent by solely interacting with its environment without any task-specific prior knowledge; it is only guided with a task-agnostic language model. Interestingly, this approach avoids the dependency to labelled datasets and inherently reduces pretrained policy flaws such as language or exposure biases. We evaluate TrufLL on two visual question generation tasks, for which we report positive results over performance and language metrics, which we then corroborate with a human evaluation. To our knowledge, it is the first approach that successfully learns a language generation policy without pre-training, using only reinforcement learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martin-etal-2022-learning">
<titleInfo>
<title>Learning Natural Language Generation with Truncated Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Quispe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Ollion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Le Corff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Strub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Pietquin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original approach to train conditional languagemodels without a supervised learning phase, by only using reinforcement learning (RL). As RL methods unsuccessfully scale to large action spaces, we dynamically truncate the vocabulary space using a generic language model. TrufLL thus enables to train a language agent by solely interacting with its environment without any task-specific prior knowledge; it is only guided with a task-agnostic language model. Interestingly, this approach avoids the dependency to labelled datasets and inherently reduces pretrained policy flaws such as language or exposure biases. We evaluate TrufLL on two visual question generation tasks, for which we report positive results over performance and language metrics, which we then corroborate with a human evaluation. To our knowledge, it is the first approach that successfully learns a language generation policy without pre-training, using only reinforcement learning.</abstract>
<identifier type="citekey">martin-etal-2022-learning</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.2</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.2</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>12</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Natural Language Generation with Truncated Reinforcement Learning
%A Martin, Alice
%A Quispe, Guillaume
%A Ollion, Charles
%A Le Corff, Sylvain
%A Strub, Florian
%A Pietquin, Olivier
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F martin-etal-2022-learning
%X This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original approach to train conditional languagemodels without a supervised learning phase, by only using reinforcement learning (RL). As RL methods unsuccessfully scale to large action spaces, we dynamically truncate the vocabulary space using a generic language model. TrufLL thus enables to train a language agent by solely interacting with its environment without any task-specific prior knowledge; it is only guided with a task-agnostic language model. Interestingly, this approach avoids the dependency to labelled datasets and inherently reduces pretrained policy flaws such as language or exposure biases. We evaluate TrufLL on two visual question generation tasks, for which we report positive results over performance and language metrics, which we then corroborate with a human evaluation. To our knowledge, it is the first approach that successfully learns a language generation policy without pre-training, using only reinforcement learning.
%R 10.18653/v1/2022.naacl-main.2
%U https://aclanthology.org/2022.naacl-main.2
%U https://doi.org/10.18653/v1/2022.naacl-main.2
%P 12-37
Markdown (Informal)
[Learning Natural Language Generation with Truncated Reinforcement Learning](https://aclanthology.org/2022.naacl-main.2) (Martin et al., NAACL 2022)
ACL
- Alice Martin, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, and Olivier Pietquin. 2022. Learning Natural Language Generation with Truncated Reinforcement Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 12–37, Seattle, United States. Association for Computational Linguistics.