In this talk, we will show how we used Randstad history of candidate placements to generate labeled CV-vacancy pairs dataset. Afterwards we fine-tune a multilingual BERT with bi encoder structure over this dataset, by adding a cosine similarity log loss layer. We will explain how using the mentioned structure helps us overcome most of the challenges described above, and how it enables us to build a maintainable and scalable pipeline to match CVs and vacancies. In addition, we show how we gain a better semantic understanding, and learn to bridge the vocabulary gap. Finally, we highlight how multilingual transformers help us handle cross language barrier and might reduce discrimination.
@article{arxiv.2109.07157,
title = {Learning to Match Job Candidates Using Multilingual Bi-Encoder BERT},
author = {Dor Lavi},
journal= {arXiv preprint arXiv:2109.07157},
year = {2021}
}
Comments
2 pages, To be presented as a main talk at RecSys '21: Fifteenth ACM Conference on Recommender Systems. arXiv admin note: substantial text overlap with arXiv:2109.06501