Mitigating Language Bias in Cross-Lingual Job Retrieval: A Recruitment Platform Perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909478441451520 |
|---|---|
| author | Laosaengpha, Napat Tativannarat, Thanit Rutherford, Attapol Chuangsuwanich, Ekapol |
| author_facet | Laosaengpha, Napat Tativannarat, Thanit Rutherford, Attapol Chuangsuwanich, Ekapol |
| contents | Understanding the textual components of resumes and job postings is critical for improving job-matching accuracy and optimizing job search systems in online recruitment platforms. However, existing works primarily focus on analyzing individual components within this information, requiring multiple specialized tools to analyze each aspect. Such disjointed methods could potentially hinder overall generalizability in recruitment-related text processing. Therefore, we propose a unified sentence encoder that utilized multi-task dual-encoder framework for jointly learning multiple component into the unified sentence encoder. The results show that our method outperforms other state-of-the-art models, despite its smaller model size. Moreover, we propose a novel metric, Language Bias Kullback-Leibler Divergence (LBKL), to evaluate language bias in the encoder, demonstrating significant bias reduction and superior cross-lingual performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03220 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating Language Bias in Cross-Lingual Job Retrieval: A Recruitment Platform Perspective Laosaengpha, Napat Tativannarat, Thanit Rutherford, Attapol Chuangsuwanich, Ekapol Computation and Language Understanding the textual components of resumes and job postings is critical for improving job-matching accuracy and optimizing job search systems in online recruitment platforms. However, existing works primarily focus on analyzing individual components within this information, requiring multiple specialized tools to analyze each aspect. Such disjointed methods could potentially hinder overall generalizability in recruitment-related text processing. Therefore, we propose a unified sentence encoder that utilized multi-task dual-encoder framework for jointly learning multiple component into the unified sentence encoder. The results show that our method outperforms other state-of-the-art models, despite its smaller model size. Moreover, we propose a novel metric, Language Bias Kullback-Leibler Divergence (LBKL), to evaluate language bias in the encoder, demonstrating significant bias reduction and superior cross-lingual performance. |
| title | Mitigating Language Bias in Cross-Lingual Job Retrieval: A Recruitment Platform Perspective |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.03220 |