# Towards Explainable Job Title Matching: Leveraging Semantic Textual Relatedness and Knowledge Graphs

arXiv: https://arxiv.org/abs/2509.09522 · HTML: https://mlsanity.com/paper/2509.09522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 76 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Evolution of Semantic Similarity -- A Survey](https://mlsanity.com/paper/2004.13820/) (2020)
- [Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming](https://mlsanity.com/paper/2010.03010/) (2020)
- [JobBERT: Understanding Job Titles through Skills](https://mlsanity.com/paper/2109.09605/) (2021)
- [Quantifying the Contextualization of Word Representations with Semantic Class Probing](https://mlsanity.com/paper/2004.12198/) (2020)
- [Job2Vec: Job Title Benchmarking with Collective Multi-View Representation Learning](https://mlsanity.com/paper/2009.07429/) (2020)
- [What Makes Sentences Semantically Related: A Textual Relatedness Dataset and Empirical Study](https://mlsanity.com/paper/2110.04845/) (2021)
- [conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers](https://mlsanity.com/paper/2109.06501/) (2021)
- [Learning Job Titles Similarity from Noisy Skill Labels](https://mlsanity.com/paper/2207.00494/) (2022)
- [A Contextualized BERT model for Knowledge Graph Completion](https://mlsanity.com/paper/2412.11016/) (2024)
- [CareerBERT: Matching Resumes to ESCO Jobs in a Shared Embedding Space for Generic Job Recommendations](https://mlsanity.com/paper/2503.02056/) (2025)
- [Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models](https://mlsanity.com/paper/2010.04486/) (2020)
- [A Co-design Study for Multi-Stakeholder Job Recommender System Explanations](https://mlsanity.com/paper/2309.05507/) (2023)
- [Explainable Multi-Stakeholder Job Recommender Systems](https://mlsanity.com/paper/2410.00654/) (2024)

## Abstract (arXiv)

Semantic Textual Relatedness (STR) captures nuanced relationships between texts that extend beyond superficial lexical similarity. In this study, we investigate STR in the context of job title matching - a key challenge in resume recommendation systems, where overlapping terms are often limited or misleading. We introduce a self-supervised hybrid architecture that combines dense sentence embeddings with domain-specific Knowledge Graphs (KGs) to improve both semantic alignment and explainability. Unlike previous work that evaluated models on aggregate performance, our approach emphasizes data stratification by partitioning the STR score continuum into distinct regions: low, medium, and high semantic relatedness. This stratified evaluation enables a fine-grained analysis of model performance across semantically meaningful subspaces. We evaluate several embedding models, both with and without KG integration via graph neural networks. The results show that fine-tuned SBERT models augmented with KGs produce consistent improvements in the high-STR region, where the RMSE is reduced by 25% over strong baselines. Our findings highlight not only the benefits of combining KGs with text embeddings, but also the importance of regional performance analysis in understanding model behavior. This granular approach reveals strengths and weaknesses hidden by global metrics, and supports more targeted model selection for use in Human Resources (HR) systems and applications where fairness, explainability, and contextual matching are essential.