Automatic Identification of Expressions of Locations in Tweet Messages using Conditional Random Fields

Published:

Fei Liu, Afshin Rahimi, Bahar Salehi, Miji Choi, Ping Tan and Long Duong (2014) Automatic Identification of Expressions of Locations in Tweet Messages using Conditional Random Fields, In Proceedings of the Australasian Language Technology Association Workshop 2014 (ALTW 2014), Melbourne, Australia, pp. 171-176.

@inproceedings{Liu+:2014,
  author    = {Fei Liu and Afshin Rahimi and Bahar Salehi and Miji Choi and Ping Tan and Long Duong},
  title     = {Automatic Identification of Expressions of Locations in Tweet Messages using Conditional Random Fields},
  booktitle = {Proceedings of the Australasian Language Technology Association Workshop 2014 (ALTW 2014)},
  year      = {2014},
  address   = {Melbourne, Australia},
  pages     = {171--176}
}

Abstract

In this paper, we propose an automatic identification model, capable of extracting expressions of locations (EoLs) within Twitter messages. Moreover, we participated in the competition of ALTA Shared Task 2014 and our best-performing system is ranked among the top 3 systems (2nd in the public leaderboard). In our model, we explored the validity of the use of a wide variety of lexical, structural and geospatial features as well as a machine learning model Conditional Random Fields (CRF). Further, we investigated the effectiveness of stacking and self-training.