@inproceedings{nandy-etal-2023-clmsm,
title = "{CLMSM}: A Multi-Task Learning Framework for Pre-training on Procedural Text",
author = "Nandy, Abhilash and
Kapadnis, Manav and
Goyal, Pawan and
Ganguly, Niloy",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.589",
doi = "10.18653/v1/2023.findings-emnlp.589",
pages = "8793--8806",
abstract = "In this paper, we propose ***CLMSM***, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. ***CLMSM*** uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using hard triplets to learn fine-grained differences across entities in the procedures, and b) a novel Mask-Step Modelling objective to learn step-wise context of a procedure. We test the performance of ***CLMSM*** on the downstream tasks of tracking entities and aligning actions between two procedures on three datasets, one of which is an open-domain dataset not conforming with the pre-training dataset. We show that ***CLMSM*** not only outperforms baselines on recipes (in-domain) but is also able to generalize to open-domain procedural NLP tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nandy-etal-2023-clmsm">
<titleInfo>
<title>CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Nandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manav</namePart>
<namePart type="family">Kapadnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose ***CLMSM***, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. ***CLMSM*** uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using hard triplets to learn fine-grained differences across entities in the procedures, and b) a novel Mask-Step Modelling objective to learn step-wise context of a procedure. We test the performance of ***CLMSM*** on the downstream tasks of tracking entities and aligning actions between two procedures on three datasets, one of which is an open-domain dataset not conforming with the pre-training dataset. We show that ***CLMSM*** not only outperforms baselines on recipes (in-domain) but is also able to generalize to open-domain procedural NLP tasks.</abstract>
<identifier type="citekey">nandy-etal-2023-clmsm</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.589</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.589</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8793</start>
<end>8806</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text
%A Nandy, Abhilash
%A Kapadnis, Manav
%A Goyal, Pawan
%A Ganguly, Niloy
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nandy-etal-2023-clmsm
%X In this paper, we propose ***CLMSM***, a domain-specific, continual pre-training framework, that learns from a large set of procedural recipes. ***CLMSM*** uses a Multi-Task Learning Framework to optimize two objectives - a) Contrastive Learning using hard triplets to learn fine-grained differences across entities in the procedures, and b) a novel Mask-Step Modelling objective to learn step-wise context of a procedure. We test the performance of ***CLMSM*** on the downstream tasks of tracking entities and aligning actions between two procedures on three datasets, one of which is an open-domain dataset not conforming with the pre-training dataset. We show that ***CLMSM*** not only outperforms baselines on recipes (in-domain) but is also able to generalize to open-domain procedural NLP tasks.
%R 10.18653/v1/2023.findings-emnlp.589
%U https://aclanthology.org/2023.findings-emnlp.589
%U https://doi.org/10.18653/v1/2023.findings-emnlp.589
%P 8793-8806
Markdown (Informal)
[CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text](https://aclanthology.org/2023.findings-emnlp.589) (Nandy et al., Findings 2023)
ACL