Skill matching at scale: freelancer-project alignment for efficient multilingual candidate retrieval

TL;DR

This paper introduces a novel multilingual neural retriever architecture that improves skill matching between projects and freelancers at scale, leveraging pre-trained language models and contrastive learning.

Contribution

The paper presents a new neural retriever architecture that effectively captures skill matching in a multilingual setting, outperforming traditional methods.

Findings

Outperforms traditional skill matching methods

Effectively captures multilingual skill similarities

Facilitates efficient large-scale freelancer-project matching

Abstract

Finding the perfect match between a job proposal and a set of freelancers is not an easy task to perform at scale, especially in multiple languages. In this paper, we propose a novel neural retriever architecture that tackles this problem in a multilingual setting. Our method encodes project descriptions and freelancer profiles by leveraging pre-trained multilingual language models. The latter are used as backbone for a custom transformer architecture that aims to keep the structure of the profiles and project. This model is trained with a contrastive loss on historical data. Thanks to several experiments, we show that this approach effectively captures skill matching similarity and facilitates efficient matching, outperforming traditional methods.