@inproceedings{ghosh-srivastava-2021-mapping-language,
title = "Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning",
author = "Ghosh, Sayan and
Srivastava, Shashank",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.125",
doi = "10.18653/v1/2021.findings-emnlp.125",
pages = "1449--1462",
abstract = "Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In this paper, we pose program generation from language as Inverse Reinforcement Learning. We introduce several interpretable reward components and jointly learn (1) a reward function that linearly combines them, and (2) a policy for program generation. Fine-tuning with our approach achieves significantly better performance than competitive methods using Reinforcement Learning (RL). On the VirtualHome framework, we get improvements of up to 9.0{\%} on the Longest Common Subsequence metric and 14.7{\%} on recall-based metrics over previous work on this framework (Puig et al., 2018). The approach is data-efficient, showing larger gains in performance in the low-data regime. Generated programs are also preferred by human evaluators over an RL-based approach, and rated higher on relevance, completeness, and human-likeness.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-srivastava-2021-mapping-language">
<titleInfo>
<title>Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sayan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In this paper, we pose program generation from language as Inverse Reinforcement Learning. We introduce several interpretable reward components and jointly learn (1) a reward function that linearly combines them, and (2) a policy for program generation. Fine-tuning with our approach achieves significantly better performance than competitive methods using Reinforcement Learning (RL). On the VirtualHome framework, we get improvements of up to 9.0% on the Longest Common Subsequence metric and 14.7% on recall-based metrics over previous work on this framework (Puig et al., 2018). The approach is data-efficient, showing larger gains in performance in the low-data regime. Generated programs are also preferred by human evaluators over an RL-based approach, and rated higher on relevance, completeness, and human-likeness.</abstract>
<identifier type="citekey">ghosh-srivastava-2021-mapping-language</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.125</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.125</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1449</start>
<end>1462</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning
%A Ghosh, Sayan
%A Srivastava, Shashank
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F ghosh-srivastava-2021-mapping-language
%X Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In this paper, we pose program generation from language as Inverse Reinforcement Learning. We introduce several interpretable reward components and jointly learn (1) a reward function that linearly combines them, and (2) a policy for program generation. Fine-tuning with our approach achieves significantly better performance than competitive methods using Reinforcement Learning (RL). On the VirtualHome framework, we get improvements of up to 9.0% on the Longest Common Subsequence metric and 14.7% on recall-based metrics over previous work on this framework (Puig et al., 2018). The approach is data-efficient, showing larger gains in performance in the low-data regime. Generated programs are also preferred by human evaluators over an RL-based approach, and rated higher on relevance, completeness, and human-likeness.
%R 10.18653/v1/2021.findings-emnlp.125
%U https://aclanthology.org/2021.findings-emnlp.125
%U https://doi.org/10.18653/v1/2021.findings-emnlp.125
%P 1449-1462
Markdown (Informal)
[Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning](https://aclanthology.org/2021.findings-emnlp.125) (Ghosh & Srivastava, Findings 2021)
ACL