Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Natural Language Processing for Human Resources: A Survey

Naoki Otani, Nikita Bhutani, Estevam Hruschka

TL;DR

This survey articulates how NLP can be systematically applied across HR activities, organizing challenges into upstream tasks (taxonomy creation, information extraction, and classification/linking) and downstream tasks (retrieval, generation, and dialogue) while addressing ethics and fairness. It highlights current methods (Transformers, multi-task learning, and LLMs) and identifies gaps, such as implicit information extraction, data scarcity, and the need for realistic datasets. The paper argues for holistic, modular NLP pipelines, knowledge transfer to other domains, and broader adoption of LLMs with careful bias controls. By outlining underrepresented tasks and data needs, it provides a roadmap for researchers and practitioners to develop scalable, fair, and impactful HR NLP solutions.

Abstract

Advances in Natural Language Processing (NLP) have the potential to transform HR processes, from recruitment to employee management. While recent breakthroughs in NLP have generated significant interest in its industrial applications, a comprehensive overview of how NLP can be applied across HR activities is still lacking. This paper discovers opportunities for researchers and practitioners to harness NLP's transformative potential in this domain. We analyze key fundamental tasks such as information extraction and text classification, and their roles in downstream applications like recommendation and language generation, while also discussing ethical concerns. Additionally, we identify gaps in current research and encourage future work to explore holistic approaches for achieving broader objectives in this field.

Natural Language Processing for Human Resources: A Survey

TL;DR

This survey articulates how NLP can be systematically applied across HR activities, organizing challenges into upstream tasks (taxonomy creation, information extraction, and classification/linking) and downstream tasks (retrieval, generation, and dialogue) while addressing ethics and fairness. It highlights current methods (Transformers, multi-task learning, and LLMs) and identifies gaps, such as implicit information extraction, data scarcity, and the need for realistic datasets. The paper argues for holistic, modular NLP pipelines, knowledge transfer to other domains, and broader adoption of LLMs with careful bias controls. By outlining underrepresented tasks and data needs, it provides a roadmap for researchers and practitioners to develop scalable, fair, and impactful HR NLP solutions.

Abstract

Advances in Natural Language Processing (NLP) have the potential to transform HR processes, from recruitment to employee management. While recent breakthroughs in NLP have generated significant interest in its industrial applications, a comprehensive overview of how NLP can be applied across HR activities is still lacking. This paper discovers opportunities for researchers and practitioners to harness NLP's transformative potential in this domain. We analyze key fundamental tasks such as information extraction and text classification, and their roles in downstream applications like recommendation and language generation, while also discussing ethical concerns. Additionally, we identify gaps in current research and encourage future work to explore holistic approaches for achieving broader objectives in this field.

Paper Structure

This paper contains 25 sections, 3 figures.

Table of Contents

  1. Introduction
  2. What is HR Concerned with?
  3. Pre-hiring:
  4. Post-hiring:
  5. Upstream Tasks
  6. Taxonomy Creation
  7. Information Extraction
  8. Classification and Entity Linking
  9. Summary
  10. Downstream Tasks
  11. Retrieval and Recommendation
  12. Language Generation
  13. Dialogue Systems
  14. Ethics, Bias, and Fairness
  15. Summary
  16. ...and 10 more sections

Figures (3)

  • Figure 1: Concept of this survey paper. We review and categorize HR-related problems through the lens of core NLP research areas.
  • Figure 2: Landscape of NLP applications within the HR domain.
  • Figure 3: The problem of job recommendation (§\ref{['sec:information-retrieval']}) is a two-sided process relying on multiple facets of information, such as expertise and requirements. Even if a job seeker prefers a particular job, the candidate may not necessarily be the best fit for the position.