Named Entity Recognition in Travel-Related Search Queries

Authors

  • Brooke Cowan Expedia, Inc.
  • Sven Zethelius Expedia, Inc.,
  • Brittany Luk Expedia, Inc.
  • Teodora Baras Expedia, Inc.
  • Prachi Ukarde Expedia, Inc.
  • Daodao Zhang Expedia, Inc.

DOI:

https://doi.org/10.1609/aaai.v29i2.19050

Abstract

This paper addresses the problem of named entity recognition (NER) in travel-related search queries. NER is an important step toward a richer understanding of user-generated inputs in information retrieval systems. NER in queries is challenging due to minimal context and few structural clues. NER in restricted-domain queries is useful in vertical search applications, for example following query classification in general search. This paper describes an efficient machine learningbased solution for the high-quality extraction of semantic entities from query inputs in a restricted-domain information retrieval setting. We apply a conditional random field (CRF) sequence model to travel-domain search queries and achieve high-accuracy results. Our approach yields an overall F1 score of 86.4% on a heldout test set, outperforming a baseline score of 82.0% on a CRF with standard features. The resulting NER classifier is currently in use in a real-life travel search engine.

AAAI 2015 Proceedings Cover

Downloads

Published

2015-01-25

How to Cite

Cowan, B., Zethelius, S., Luk, B., Baras, T., Ukarde, P., & Zhang, D. (2015). Named Entity Recognition in Travel-Related Search Queries. Proceedings of the AAAI Conference on Artificial Intelligence, 29(2), 3935-3941. https://doi.org/10.1609/aaai.v29i2.19050

Issue

Vol. 29 No. 2 (2015): The Twenty-Seventh Conference on Innovative Applications of Artificial Intelligence

Section

IAAI Emerging Application Papers