@inproceedings{lin-etal-2022-inferring,
title = "Inferring Rewards from Language in Context",
author = "Lin, Jessy and
Fried, Daniel and
Klein, Dan and
Dragan, Anca",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.585",
doi = "10.18653/v1/2022.acl-long.585",
pages = "8546--8560",
abstract = "In classic instruction following, language like {``}I{'}d like the JetBlue flight{''} maps to actions (e.g., selecting that flight). However, language also conveys information about a user{'}s underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. We present a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences. On a new interactive flight{--}booking task with natural language, our model more accurately infers rewards and predicts optimal actions in unseen environments, in comparison to past work that first maps language to actions (instruction following) and then maps actions to rewards (inverse reinforcement learning).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2022-inferring">
<titleInfo>
<title>Inferring Rewards from Language in Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anca</namePart>
<namePart type="family">Dragan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In classic instruction following, language like “I’d like the JetBlue flight” maps to actions (e.g., selecting that flight). However, language also conveys information about a user’s underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. We present a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences. On a new interactive flight–booking task with natural language, our model more accurately infers rewards and predicts optimal actions in unseen environments, in comparison to past work that first maps language to actions (instruction following) and then maps actions to rewards (inverse reinforcement learning).</abstract>
<identifier type="citekey">lin-etal-2022-inferring</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.585</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.585</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>8546</start>
<end>8560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inferring Rewards from Language in Context
%A Lin, Jessy
%A Fried, Daniel
%A Klein, Dan
%A Dragan, Anca
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F lin-etal-2022-inferring
%X In classic instruction following, language like “I’d like the JetBlue flight” maps to actions (e.g., selecting that flight). However, language also conveys information about a user’s underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. We present a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences. On a new interactive flight–booking task with natural language, our model more accurately infers rewards and predicts optimal actions in unseen environments, in comparison to past work that first maps language to actions (instruction following) and then maps actions to rewards (inverse reinforcement learning).
%R 10.18653/v1/2022.acl-long.585
%U https://aclanthology.org/2022.acl-long.585
%U https://doi.org/10.18653/v1/2022.acl-long.585
%P 8546-8560
Markdown (Informal)
[Inferring Rewards from Language in Context](https://aclanthology.org/2022.acl-long.585) (Lin et al., ACL 2022)
ACL
- Jessy Lin, Daniel Fried, Dan Klein, and Anca Dragan. 2022. Inferring Rewards from Language in Context. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8546–8560, Dublin, Ireland. Association for Computational Linguistics.