Multitask Learning for Query Segmentation in Job Search

Published:

Bahar Salehi, Fei Liu, Timothy Baldwin and Wilson Wong (2018) Multitask Learning for Query Segmentation in Job Search, In Proceedings of the 8th International Conference on the Theory of Information Retrieval, Tianjin, China, pp. 179-182. Best Paper Award

@InProceedings{Salehi+:2018,
  author    = {Salehi, Bahar and Liu, Fei  and  Baldwin, Timothy and Wong, Wilson},
  title     = {Multitask Learning for Query Segmentation in Job Search},
  booktitle = {Proceedings of the 8th International Conference on the Theory of Information Retrieval},
  year      = {2018},
  address   = {Tianjin, China},
  pages     = {179--182}
}

Abstract

In this paper, we present the first attempt to use multitask learning for query segmentation. We use the semantic category of the words as an auxiliary task and show that segmentation improves when the model is also trained to predict the semantic category of the query terms, outperforming benchmark methods over a novel dataset from a popular job search engine. Our further experiments show that the task of modeling the query term semantics performs better as a standalone task, without adding segmentation as an auxiliary task.