@inproceedings{luo-etal-2022-masked,
title = "Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering",
author = "Luo, Xuan and
Fan, Chuang and
Zhang, Yice and
Jiang, Wanguo and
Qin, Bing and
Xu, Ruifeng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.233",
doi = "10.18653/v1/2022.findings-emnlp.233",
pages = "3200--3213",
abstract = "We propose a simple ranking strategy to solve a generative commonsense question answering (QA) problem. Compared with multiple-choice QA, it is challenging because the answers to a question are not unique and they are supposed to be popular and diverse. Our strategy exploits the dataset itself and negative samples that we collect from WordNet to train a ranker that picks out the most popular answers for commonsense questions. The effectiveness of our strategy is verified on different pre-trained masked language models (MLMs) in a pipeline framework, where an MLM reranks the generated answers. Further, we explore an end-to-end framework where MLMs are utilized to guide the generation of generative language models (GLMs). Taking advantage of reinforcement learning, we apply policy gradient to train a GLM with the rewards fed back by an MLM. Empirical results on ProtoQA dataset demonstrate that MLMs can acquire the ability to distinguish the popular answers and improve the typical answer generation of GLMs as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2022-masked">
<titleInfo>
<title>Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuang</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yice</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanguo</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a simple ranking strategy to solve a generative commonsense question answering (QA) problem. Compared with multiple-choice QA, it is challenging because the answers to a question are not unique and they are supposed to be popular and diverse. Our strategy exploits the dataset itself and negative samples that we collect from WordNet to train a ranker that picks out the most popular answers for commonsense questions. The effectiveness of our strategy is verified on different pre-trained masked language models (MLMs) in a pipeline framework, where an MLM reranks the generated answers. Further, we explore an end-to-end framework where MLMs are utilized to guide the generation of generative language models (GLMs). Taking advantage of reinforcement learning, we apply policy gradient to train a GLM with the rewards fed back by an MLM. Empirical results on ProtoQA dataset demonstrate that MLMs can acquire the ability to distinguish the popular answers and improve the typical answer generation of GLMs as well.</abstract>
<identifier type="citekey">luo-etal-2022-masked</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.233</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.233</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3200</start>
<end>3213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering
%A Luo, Xuan
%A Fan, Chuang
%A Zhang, Yice
%A Jiang, Wanguo
%A Qin, Bing
%A Xu, Ruifeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F luo-etal-2022-masked
%X We propose a simple ranking strategy to solve a generative commonsense question answering (QA) problem. Compared with multiple-choice QA, it is challenging because the answers to a question are not unique and they are supposed to be popular and diverse. Our strategy exploits the dataset itself and negative samples that we collect from WordNet to train a ranker that picks out the most popular answers for commonsense questions. The effectiveness of our strategy is verified on different pre-trained masked language models (MLMs) in a pipeline framework, where an MLM reranks the generated answers. Further, we explore an end-to-end framework where MLMs are utilized to guide the generation of generative language models (GLMs). Taking advantage of reinforcement learning, we apply policy gradient to train a GLM with the rewards fed back by an MLM. Empirical results on ProtoQA dataset demonstrate that MLMs can acquire the ability to distinguish the popular answers and improve the typical answer generation of GLMs as well.
%R 10.18653/v1/2022.findings-emnlp.233
%U https://aclanthology.org/2022.findings-emnlp.233
%U https://doi.org/10.18653/v1/2022.findings-emnlp.233
%P 3200-3213
Markdown (Informal)
[Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering](https://aclanthology.org/2022.findings-emnlp.233) (Luo et al., Findings 2022)
ACL