[论文解读] Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

Shuqing Bian, Xu Chen+6 more|arXiv (Cornell University)|Sep 25, 2020

Advanced Graph Neural Networks参考文献 30被引用 5

一句话总结

本文提出了一种多视角协同教学网络，通过结合基于文本的匹配模型与基于关系的匹配模型，在稀疏且嘈杂的交互数据下提升了职位-简历匹配效果。通过共享表示并利用协同教学过滤噪声样本，该模型增强了鲁棒性，并在基准数据集上实现了最先进性能。

ABSTRACT

With the ever-increasing growth of online recruitment data, job-resume matching has become an important task to automatically match jobs with suitable resumes. This task is typically casted as a supervised text matching problem. Supervised learning is powerful when the labeled data is sufficient. However, on online recruitment platforms, job-resume interaction data is sparse and noisy, which affects the performance of job-resume match algorithms. To alleviate these problems, in this paper, we propose a novel multi-view co-teaching network from sparse interaction data for job-resume matching. Our network consists of two major components, namely text-based matching model and relation-based matching model. The two parts capture semantic compatibility in two different views, and complement each other. In order to address the challenges from sparse and noisy data, we design two specific strategies to combine the two components. First, two components share the learned parameters or representations, so that the original representations of each component can be enhanced. More importantly, we adopt a co-teaching mechanism to reduce the influence of noise in training data. The core idea is to let the two components help each other by selecting more reliable training instances. The two strategies focus on representation enhancement and data enhancement, respectively. Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data. Experiment results have demonstrated that our model is able to outperform state-of-the-art methods for job-resume matching.

研究动机与目标

• 解决在线招聘平台中职位-简历交互数据稀疏且嘈杂的挑战。
• 在标注的交互数据有限且不可靠的情况下，提升匹配性能。
• 构建一个统一模型，同时利用职位-简历图中的语义文本匹配与关系结构。
• 通过协同教学与表示增强策略，降低噪声负样本的影响。

提出的方法

• 提出一种具有两个分支的多视角协同教学网络：基于文本的匹配模型与基于关系的匹配模型。
• 在两个模型之间共享学习到的表示，通过表示协同适应增强特征学习。
• 实施协同教学机制，使每个模型根据另一模型的预测结果选择可靠的训练实例，以减少噪声影响。
• 通过式(12)和式(14)实现重加权与过滤策略，降低不一致或低质量负样本的权重。
• 从共享技能与职位中构建知识图，以建模职位与简历之间的关系连接。
• 使用对比学习目标，在匹配对与不匹配对上端到端训练模型。

实验结果

研究问题

• RQ1 在交互数据稀疏的情况下，多视角学习框架能否提升职位-简历匹配性能？
• RQ2 协同教学在过滤职位-简历匹配中的噪声负样本方面有多有效？
• RQ3 文本与关系视角之间共享表示在多大程度上提升了模型的鲁棒性？
• RQ4 当标注数据有限时，从知识图中整合关系信号是否能提升匹配准确率？

主要发现

• 在Technology与Finance数据集上，所提模型在AUC与MAP指标上均优于最先进基线模型。
• 协同教学机制通过过滤噪声负样本上的不一致预测，显著提升了模型鲁棒性。
• 文本与关系模型之间的表示共享，带来了更稳定且可泛化的特征学习。
• 案例研究显示，该模型能正确识别出错误的负样本（如线下面试），而标准模型则将其错误分类为负样本。
• 即使文本相似度较低，基于关系的模型仍能通过结构连接捕捉匹配度，体现出互补优势。