@inproceedings{liu-etal-2023-language,
title = "A Language-First Approach for Procedure Planning",
author = "Liu, Jiateng and
Li, Sha and
Wang, Zhenhailong and
Li, Manling and
Ji, Heng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.122",
doi = "10.18653/v1/2023.findings-acl.122",
pages = "1941--1954",
abstract = "Procedure planning, or the ability to predict a series of steps that can achieve a given goal conditioned on the current observation, is critical for building intelligent embodied agents that can assist users in everyday tasks. Encouraged by the recent success of language models (LMs) for zero-shot and few-shot planning, we hypothesize that LMs may be equipped with stronger priors for planning compared to their visual counterparts. To this end, we propose a language-first procedure planning framework with a modularized design: we first align the current and goal observations with corresponding steps and then use a pre-trained LM to predict the intermediate steps. Under this framework, we find that using an image captioning model for alignment can already match state-of-the-art performance and by designing a double retrieval model conditioned over current and goal observations jointly, we can achieve large improvements (19.2{\%}-98.9{\%} relatively higher success rate than state-of-the-art) on both COIN and CrossTask benchmarks. Our work verifies the planning ability of LMs and demonstrates how LMs can serve as a powerful {``}reasoning engine{''} even when the input is provided in another modality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-language">
<titleInfo>
<title>A Language-First Approach for Procedure Planning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiateng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sha</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhailong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Procedure planning, or the ability to predict a series of steps that can achieve a given goal conditioned on the current observation, is critical for building intelligent embodied agents that can assist users in everyday tasks. Encouraged by the recent success of language models (LMs) for zero-shot and few-shot planning, we hypothesize that LMs may be equipped with stronger priors for planning compared to their visual counterparts. To this end, we propose a language-first procedure planning framework with a modularized design: we first align the current and goal observations with corresponding steps and then use a pre-trained LM to predict the intermediate steps. Under this framework, we find that using an image captioning model for alignment can already match state-of-the-art performance and by designing a double retrieval model conditioned over current and goal observations jointly, we can achieve large improvements (19.2%-98.9% relatively higher success rate than state-of-the-art) on both COIN and CrossTask benchmarks. Our work verifies the planning ability of LMs and demonstrates how LMs can serve as a powerful “reasoning engine” even when the input is provided in another modality.</abstract>
<identifier type="citekey">liu-etal-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.122</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.122</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1941</start>
<end>1954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Language-First Approach for Procedure Planning
%A Liu, Jiateng
%A Li, Sha
%A Wang, Zhenhailong
%A Li, Manling
%A Ji, Heng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-language
%X Procedure planning, or the ability to predict a series of steps that can achieve a given goal conditioned on the current observation, is critical for building intelligent embodied agents that can assist users in everyday tasks. Encouraged by the recent success of language models (LMs) for zero-shot and few-shot planning, we hypothesize that LMs may be equipped with stronger priors for planning compared to their visual counterparts. To this end, we propose a language-first procedure planning framework with a modularized design: we first align the current and goal observations with corresponding steps and then use a pre-trained LM to predict the intermediate steps. Under this framework, we find that using an image captioning model for alignment can already match state-of-the-art performance and by designing a double retrieval model conditioned over current and goal observations jointly, we can achieve large improvements (19.2%-98.9% relatively higher success rate than state-of-the-art) on both COIN and CrossTask benchmarks. Our work verifies the planning ability of LMs and demonstrates how LMs can serve as a powerful “reasoning engine” even when the input is provided in another modality.
%R 10.18653/v1/2023.findings-acl.122
%U https://aclanthology.org/2023.findings-acl.122
%U https://doi.org/10.18653/v1/2023.findings-acl.122
%P 1941-1954
Markdown (Informal)
[A Language-First Approach for Procedure Planning](https://aclanthology.org/2023.findings-acl.122) (Liu et al., Findings 2023)
ACL
- Jiateng Liu, Sha Li, Zhenhailong Wang, Manling Li, and Heng Ji. 2023. A Language-First Approach for Procedure Planning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1941–1954, Toronto, Canada. Association for Computational Linguistics.