# conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers

arXiv: https://arxiv.org/abs/2109.06501 · HTML: https://mlsanity.com/paper/2109.06501/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [A Survey Of Cross-lingual Word Embedding Models](https://mlsanity.com/paper/1706.04902/) (2017)
- [Evolution of Semantic Similarity -- A Survey](https://mlsanity.com/paper/2004.13820/) (2020)
- [Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach](https://mlsanity.com/paper/1812.08947/) (2018)
- [Learning to Match Jobs with Resumes from Sparse Interaction Data using Multi-View Co-Teaching Network](https://mlsanity.com/paper/2009.13299/) (2020)
- [Towards Deep and Representation Learning for Talent Search at LinkedIn](https://mlsanity.com/paper/1809.06473/) (2018)
- [Embedding-based Recommender System for Job to Candidate Matching on Scale](https://mlsanity.com/paper/2107.00221/) (2021)
- [End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT](https://mlsanity.com/paper/1910.03089/) (2019)

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics](https://mlsanity.com/paper/2307.03195/) (2023)
- [Career Path Prediction using Resume Representation Learning and Skill-based Matching](https://mlsanity.com/paper/2310.15636/) (2023)
- [Natural Language Processing for Human Resources: A Survey](https://mlsanity.com/paper/2410.16498/) (2024)
- [CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations](https://mlsanity.com/paper/2503.02056/) (2025)
- [The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of Paintings](https://mlsanity.com/paper/2303.08182/) (2023)
- [Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management](https://mlsanity.com/paper/2507.13275/) (2025)
- [Skill matching at scale: freelancer-project alignment for efficient multilingual candidate retrieval](https://mlsanity.com/paper/2409.12097/) (2024)
- [An Efficient Long-Context Ranking Architecture With Calibrated LLM Distillation: Application to Person-Job Fit](https://mlsanity.com/paper/2601.10321/) (2026)
- [OKRA: an Explainable, Heterogeneous, Multi-Stakeholder Job Recommender System](https://mlsanity.com/paper/2504.07108/) (2025)
- [Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs](https://mlsanity.com/paper/2509.09522/) (2025)
- [UniSkill: A Dataset for Matching University Curricula to Professional Competencies](https://mlsanity.com/paper/2603.03134/) (2026)
- [How Supply Chain Dependencies Complicate Bias Measurement and Accountability Attribution in AI Hiring Applications](https://mlsanity.com/paper/2604.22679/) (2026)
- [Overview of the TalentCLEF 2026: Skill and Job Title Intelligence for Human Capital Management](https://mlsanity.com/paper/2606.31692/) (2026)

## Abstract (arXiv)

In this paper we focus on constructing useful embeddings of textual information in vacancies and resumes, which we aim to incorporate as features into job to job seeker matching models alongside other features. We explain our task where noisy data from parsed resumes, heterogeneous nature of the different sources of data, and crosslinguality and multilinguality present domain-specific challenges. We address these challenges by fine-tuning a Siamese Sentence-BERT (SBERT) model, which we call conSultantBERT, using a large-scale, real-world, and high quality dataset of over 270,000 resume-vacancy pairs labeled by our staffing consultants. We show how our fine-tuned model significantly outperforms unsupervised and supervised baselines that rely on TF-IDF-weighted feature vectors and BERT embeddings. In addition, we find our model successfully matches cross-lingual and multilingual textual content.