@inproceedings{peng-liu-2022-expertplm,
title = "{E}xpert{PLM}: Pre-training Expert Representation for Expert Finding",
author = "Peng, Qiyao and
Liu, Hongtao",
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.74",
doi = "10.18653/v1/2022.findings-emnlp.74",
pages = "1043--1052",
abstract = "Expert Finding is an important task in Community Question Answering (CQA) platforms, which could help route questions to potential users to answer. The key is to learn representations of experts based on their historical answered questions accurately. In this paper, inspired by the strong text understanding ability of Pretrained Language modelings (PLMs), we propose a pre-training and fine-tuning expert finding framework. The core is that we design an expert-level pre-training paradigm, that effectively integrates expert interest and expertise simultaneously. Specifically different from the typical corpus-level pre-training, we treat each expert as the basic pre-training unit including all the historical answered question titles of the expert, which could fully indicate the expert interests for questions. Besides, we integrate the vote score information along with each answer of the expert into the pre-training phrase to model the expert ability explicitly. Finally, we propose a novel reputation-augmented Masked Language Model (MLM) pre-training strategy to capture the expert reputation information. In this way, our method could learn expert representation comprehensively, which then will be adopted and fine-tuned in the down-streaming expert-finding task. Extensive experimental results on six real-world CQA datasets demonstrate the effectiveness of our method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-liu-2022-expertplm">
<titleInfo>
<title>ExpertPLM: Pre-training Expert Representation for Expert Finding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongtao</namePart>
<namePart type="family">Liu</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>Expert Finding is an important task in Community Question Answering (CQA) platforms, which could help route questions to potential users to answer. The key is to learn representations of experts based on their historical answered questions accurately. In this paper, inspired by the strong text understanding ability of Pretrained Language modelings (PLMs), we propose a pre-training and fine-tuning expert finding framework. The core is that we design an expert-level pre-training paradigm, that effectively integrates expert interest and expertise simultaneously. Specifically different from the typical corpus-level pre-training, we treat each expert as the basic pre-training unit including all the historical answered question titles of the expert, which could fully indicate the expert interests for questions. Besides, we integrate the vote score information along with each answer of the expert into the pre-training phrase to model the expert ability explicitly. Finally, we propose a novel reputation-augmented Masked Language Model (MLM) pre-training strategy to capture the expert reputation information. In this way, our method could learn expert representation comprehensively, which then will be adopted and fine-tuned in the down-streaming expert-finding task. Extensive experimental results on six real-world CQA datasets demonstrate the effectiveness of our method.</abstract>
<identifier type="citekey">peng-liu-2022-expertplm</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.74</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.74</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1043</start>
<end>1052</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExpertPLM: Pre-training Expert Representation for Expert Finding
%A Peng, Qiyao
%A Liu, Hongtao
%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 peng-liu-2022-expertplm
%X Expert Finding is an important task in Community Question Answering (CQA) platforms, which could help route questions to potential users to answer. The key is to learn representations of experts based on their historical answered questions accurately. In this paper, inspired by the strong text understanding ability of Pretrained Language modelings (PLMs), we propose a pre-training and fine-tuning expert finding framework. The core is that we design an expert-level pre-training paradigm, that effectively integrates expert interest and expertise simultaneously. Specifically different from the typical corpus-level pre-training, we treat each expert as the basic pre-training unit including all the historical answered question titles of the expert, which could fully indicate the expert interests for questions. Besides, we integrate the vote score information along with each answer of the expert into the pre-training phrase to model the expert ability explicitly. Finally, we propose a novel reputation-augmented Masked Language Model (MLM) pre-training strategy to capture the expert reputation information. In this way, our method could learn expert representation comprehensively, which then will be adopted and fine-tuned in the down-streaming expert-finding task. Extensive experimental results on six real-world CQA datasets demonstrate the effectiveness of our method.
%R 10.18653/v1/2022.findings-emnlp.74
%U https://aclanthology.org/2022.findings-emnlp.74
%U https://doi.org/10.18653/v1/2022.findings-emnlp.74
%P 1043-1052
Markdown (Informal)
[ExpertPLM: Pre-training Expert Representation for Expert Finding](https://aclanthology.org/2022.findings-emnlp.74) (Peng & Liu, Findings 2022)
ACL