TAROT: A Hierarchical Framework with Multitask Co-Pretraining on Semi-Structured Data towards Effective Person-Job Fit (2401.07525v2)
Abstract: Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained LLMs have further enhanced the effectiveness by leveraging richer textual information in user profiles and job descriptions apart from user behavior features and job metadata. However, the general domain-oriented design struggles to capture the unique structural information within user profiles and job descriptions, leading to a loss of latent semantic correlations. We propose TAROT, a hierarchical multitask co-pretraining framework, to better utilize structural and semantic information for informative text embeddings. TAROT targets semi-structured text in profiles and jobs, and it is co-pretained with multi-grained pretraining tasks to constrain the acquired semantic information at each level. Experiments on a real-world LinkedIn dataset show significant performance improvements, proving its effectiveness in person-job fit tasks.
- “The unemployment crisis,” 1994.
- Society For Human Resource Management, “Human capital benchmarking report,” 2016.
- “A research of job recommendation system based on collaborative filtering,” in 2014 Seventh International Symposium on Computational Intelligence and Design, 2014, vol. 1, pp. 533–538.
- “A recommender system for job seeking and recruiting website,” 05 2013, pp. 963–966.
- “Enhancing person-job fit for talent recruitment: An ability-aware neural network approach,” 06 2018, pp. 25–34.
- “Domain adaptation for person-job fit with transferable deep global match network,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, Nov. 2019, pp. 4810–4820, Association for Computational Linguistics.
- “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, Minnesota, June 2019, pp. 4171–4186, Association for Computational Linguistics.
- “Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,” arXiv preprint arXiv:1910.13461, 2019.
- “Language models are few-shot learners,” Advances in neural information processing systems, vol. 33, pp. 1877–1901, 2020.
- “Learning to match jobs with resumes from sparse interaction data using multi-view co-teaching network,” in Proceedings of the 29th ACM International Conference on Information and Knowledge Management, New York, NY, USA, 2020, CIKM ’20, p. 65–74, Association for Computing Machinery.
- “Deep natural language processing for linkedin search,” CoRR, vol. abs/2108.13300, 2021.
- “Sentence-bert: Sentence embeddings using siamese bert-networks,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 3982–3992.
- “On the sentence embeddings from pre-trained language models,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, pp. 9119–9130.
- “Funnel-transformer: Filtering out sequential redundancy for efficient language processing,” 06 2020.
- “On the importance of pre-training data volume for compact language models,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online, Nov. 2020, pp. 7853–7858, Association for Computational Linguistics.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.