Reconstructing the house from the ad: Structured prediction on real estate classifieds

Giannis Bekoulis, Johannes Deleu, Thomas Demeester, Chris Develder

[How to correct problems with metadata yourself]


Abstract
In this paper, we address the (to the best of our knowledge) new problem of extracting a structured description of real estate properties from their natural language descriptions in classifieds. We survey and present several models to (a) identify important entities of a property (e.g.,rooms) from classifieds and (b) structure them into a tree format, with the entities as nodes and edges representing a part-of relation. Experiments show that a graph-based system deriving the tree from an initially fully connected entity graph, outperforms a transition-based system starting from only the entity nodes, since it better reconstructs the tree.
Anthology ID:
E17-2044
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
274–279
Language:
URL:
https://aclanthology.org/E17-2044
DOI:
Bibkey:
Cite (ACL):
Giannis Bekoulis, Johannes Deleu, Thomas Demeester, and Chris Develder. 2017. Reconstructing the house from the ad: Structured prediction on real estate classifieds. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 274–279, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Reconstructing the house from the ad: Structured prediction on real estate classifieds (Bekoulis et al., EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/E17-2044.pdf
Code
 bekou/ad_data