@inproceedings{wang-etal-2022-ascm,
title = "{ASCM}: An Answer Space Clustered Prompting Method without Answer Engineering",
author = "Wang, Zhen and
Yang, Yating and
Xi, Zhou and
Ma, Bo and
Wang, Lei and
Dong, Rui and
Anwar, Azmat",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.193/",
doi = "10.18653/v1/2022.findings-acl.193",
pages = "2455--2469",
abstract = "Prompt-based learning, which exploits knowledge from pre-trained language models by providing textual prompts and designing appropriate answer-category mapping methods, has achieved impressive successes on few-shot text classification and natural language inference (NLI). Because of the diverse linguistic expression, there exist many answer tokens for the same category. However, both manual answer design and automatic answer search constrain answer space and therefore hardly achieve ideal performance. To address this issue, we propose an answer space clustered prompting model (ASCM) together with a synonym initialization method (SI) which automatically categorizes all answer tokens in a semantic-clustered embedding space. We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models. Extensive experiments demonstrate that our ASCM+SL significantly outperforms existing state-of-the-art techniques in few-shot settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-ascm">
<titleInfo>
<title>ASCM: An Answer Space Clustered Prompting Method without Answer Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azmat</namePart>
<namePart type="family">Anwar</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>Findings of the Association for Computational Linguistics: ACL 2022</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>Prompt-based learning, which exploits knowledge from pre-trained language models by providing textual prompts and designing appropriate answer-category mapping methods, has achieved impressive successes on few-shot text classification and natural language inference (NLI). Because of the diverse linguistic expression, there exist many answer tokens for the same category. However, both manual answer design and automatic answer search constrain answer space and therefore hardly achieve ideal performance. To address this issue, we propose an answer space clustered prompting model (ASCM) together with a synonym initialization method (SI) which automatically categorizes all answer tokens in a semantic-clustered embedding space. We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models. Extensive experiments demonstrate that our ASCM+SL significantly outperforms existing state-of-the-art techniques in few-shot settings.</abstract>
<identifier type="citekey">wang-etal-2022-ascm</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.193</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.193/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2455</start>
<end>2469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ASCM: An Answer Space Clustered Prompting Method without Answer Engineering
%A Wang, Zhen
%A Yang, Yating
%A Xi, Zhou
%A Ma, Bo
%A Wang, Lei
%A Dong, Rui
%A Anwar, Azmat
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F wang-etal-2022-ascm
%X Prompt-based learning, which exploits knowledge from pre-trained language models by providing textual prompts and designing appropriate answer-category mapping methods, has achieved impressive successes on few-shot text classification and natural language inference (NLI). Because of the diverse linguistic expression, there exist many answer tokens for the same category. However, both manual answer design and automatic answer search constrain answer space and therefore hardly achieve ideal performance. To address this issue, we propose an answer space clustered prompting model (ASCM) together with a synonym initialization method (SI) which automatically categorizes all answer tokens in a semantic-clustered embedding space. We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models. Extensive experiments demonstrate that our ASCM+SL significantly outperforms existing state-of-the-art techniques in few-shot settings.
%R 10.18653/v1/2022.findings-acl.193
%U https://aclanthology.org/2022.findings-acl.193/
%U https://doi.org/10.18653/v1/2022.findings-acl.193
%P 2455-2469
Markdown (Informal)
[ASCM: An Answer Space Clustered Prompting Method without Answer Engineering](https://aclanthology.org/2022.findings-acl.193/) (Wang et al., Findings 2022)
ACL