@inproceedings{qu-etal-2022-commonsense,
title = "Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in {E}-commerce",
author = "Qu, Yincen and
Zhang, Ningyu and
Chen, Hui and
Dai, Zelin and
Wang, Chengming and
Wang, Xiaoyu and
Chen, Qiang and
Chen, Huajun",
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.2",
doi = "10.18653/v1/2022.findings-emnlp.2",
pages = "14--27",
abstract = "In e-commerce, the salience of commonsense knowledge (CSK) is beneficial for widespread applications such as product search and recommendation. For example, when users search for {``}running{''} in e-commerce, they would like to find products highly related to running, such as {``}running shoes{''} rather than {``}shoes{''}. Nevertheless, many existing CSK collections rank statements solely by confidence scores, and there is no information about which ones are salient from a human perspective. In this work, we define the task of supervised salience evaluation, where given a CSK triple, the model is required to learn whether the triple is salient or not. In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation. We conduct experiments in the dataset with several representative baseline models. The experimental results show that salience evaluation is a hard task where models perform poorly on our evaluation set. We further propose a simple but effective approach, PMI-tuning, which shows promise for solving this novel problem. Code is available in \url{https://github.com/OpenBGBenchmark/OpenBG-CSK}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qu-etal-2022-commonsense">
<titleInfo>
<title>Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yincen</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ningyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zelin</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengming</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huajun</namePart>
<namePart type="family">Chen</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>In e-commerce, the salience of commonsense knowledge (CSK) is beneficial for widespread applications such as product search and recommendation. For example, when users search for “running” in e-commerce, they would like to find products highly related to running, such as “running shoes” rather than “shoes”. Nevertheless, many existing CSK collections rank statements solely by confidence scores, and there is no information about which ones are salient from a human perspective. In this work, we define the task of supervised salience evaluation, where given a CSK triple, the model is required to learn whether the triple is salient or not. In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation. We conduct experiments in the dataset with several representative baseline models. The experimental results show that salience evaluation is a hard task where models perform poorly on our evaluation set. We further propose a simple but effective approach, PMI-tuning, which shows promise for solving this novel problem. Code is available in https://github.com/OpenBGBenchmark/OpenBG-CSK.</abstract>
<identifier type="citekey">qu-etal-2022-commonsense</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.2</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.2</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>14</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce
%A Qu, Yincen
%A Zhang, Ningyu
%A Chen, Hui
%A Dai, Zelin
%A Wang, Chengming
%A Wang, Xiaoyu
%A Chen, Qiang
%A Chen, Huajun
%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 qu-etal-2022-commonsense
%X In e-commerce, the salience of commonsense knowledge (CSK) is beneficial for widespread applications such as product search and recommendation. For example, when users search for “running” in e-commerce, they would like to find products highly related to running, such as “running shoes” rather than “shoes”. Nevertheless, many existing CSK collections rank statements solely by confidence scores, and there is no information about which ones are salient from a human perspective. In this work, we define the task of supervised salience evaluation, where given a CSK triple, the model is required to learn whether the triple is salient or not. In addition to formulating the new task, we also release a new Benchmark dataset of Salience Evaluation in E-commerce (BSEE) and hope to promote related research on commonsense knowledge salience evaluation. We conduct experiments in the dataset with several representative baseline models. The experimental results show that salience evaluation is a hard task where models perform poorly on our evaluation set. We further propose a simple but effective approach, PMI-tuning, which shows promise for solving this novel problem. Code is available in https://github.com/OpenBGBenchmark/OpenBG-CSK.
%R 10.18653/v1/2022.findings-emnlp.2
%U https://aclanthology.org/2022.findings-emnlp.2
%U https://doi.org/10.18653/v1/2022.findings-emnlp.2
%P 14-27
Markdown (Informal)
[Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce](https://aclanthology.org/2022.findings-emnlp.2) (Qu et al., Findings 2022)
ACL
- Yincen Qu, Ningyu Zhang, Hui Chen, Zelin Dai, Chengming Wang, Xiaoyu Wang, Qiang Chen, and Huajun Chen. 2022. Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 14–27, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.