EMNLP Findings2023
Contrastive Pre-training for Personalized Expert Finding
Abstract
Expert finding could help route questions to potential suitable users to answer in Community Question Answering (CQA) platforms. Hence it is essential to learn accurate representations of experts and questions according to the question text articles. Recently the pre-training and fine-tuning paradigms are powerful for natural language understanding, which has the potential for better question modeling and expert finding. Inspired by this, we propose a CQA-domain Contrastive Pre-training framework for Expert Finding, named CPEF, which could learn more comprehensive question representations. Specifically, considering that there is semantic complementation between question titles and bodies, during the domain pretraining phase, we propose a title-body contrastive learning task to enhance question representations, which directly treats the question title and the corresponding body as positive samples of each other, instead of designing extra data-augmentation strategies. Furthermore, a personalized tuning network is proposed to inject the personalized preferences of different experts during the fine-tuning phase. Extensive experimental results on six real-world datasets demonstrate that our method could achieve superior performance for expert finding.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on3
- Towards Universal Sequence Representation Learning for Recommender SystemsYupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li et al.KDD 2022 · 245 citations
- PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervisionChuhan Wu, Fangzhao Wu, Tao Qi, Jianxun Lian et al.EMNLP Findings 2020 · 36 citations
- ExpertPLM: Pre-training Expert Representation for Expert FindingQiyao Peng, Hongtao LiuEMNLP Findings 2022 · 8 citations
Related papers
- Towards a Multi-View Attentive Matching for Personalized Expert FindingQiyao Peng, Hongtao Liu, Yinghui Wang, Hongyan Xu et al.WWW 2022 · 20 citations
- KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question AnsweringJianing Wang, Chengyu Wang, Minghui Qiu, Qiuhui Shi et al.EMNLP 2022 · 16 citations
- Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QASeonhoon Kim, Seohyeong Jeong, Eunbyul Kim, Inho Kang et al.AAAI 2021 · 44 citations
- Contrastive Domain Adaptation for Question Answering using Limited Text CorporaZhenrui Yue, Bernhard Kratzwald, Stefan FeuerriegelEMNLP 2021 · 22 citations
- Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-trainingYuting Ning, Zhenya Huang, Xin Lin, Enhong Chen et al.AAAI 2023 · 10 citations
