Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network

Automatically matching jobs with suitable candidates can accelerate the recruitment process. However, this task is difficult due to the sparseness and noisiness of the data. A recent study on proposes a multi-view co-teaching network that combines both text-based matching and relation-based matching. The former relies on semantic similarity while the latter constructs a job-resume relation graph, and then develops a matching model using relational graph neural networks.

A job interview. Image credit: Waseem Farooq via Pxhere, CC0 Public Domain

A job interview. Image credit: Waseem Farooq via Pxhere, CC0 Public Domain

The two models are combined using two strategies: firstly, the two parts share the learned parameters and representations. Secondly, the impact of noise is reduced by employing co-teaching to help to select “high quality” training samples. The experiments on real-world datasets demonstrate that the suggested approach outperforms current matching methods, which usually focus on either the relations or the semantics of the jobs and resumes.

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.