A Novel Ranking Model for Product Name Extraction

DOI

10.2991/mmebc-16.2016.212How to use a DOI?

Keywords

Learning to Rank, Product Name, Extraction, SVM

Abstract

The Internet contains large amounts of information, which are valuable to the researchers. Since manual product name collection needs large human efforts and also time consuming, extracting keywords automatically become a hot topic. This paper addresses the issue of automatic extraction for agricultural product name. Previously, this problem was formalized as classification and learning methods for classification were utilized. In this paper, we transform the product name extraction problem into a ranking problem and employ a learning to rank method to solve the task. Specifically, we utilize the ranking SVM to extract the agricultural product name. Experimental results on real life datasets demonstrate that our novel ranking method outperforms the baseline methods.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ling Shen
AU  - Qingxi Peng
AU  - Nian Li
PY  - 2016/06
DA  - 2016/06
TI  - A Novel Ranking Model for Product Name Extraction
BT  - Proceedings of the 2016 6th International Conference on Machinery, Materials, Environment, Biotechnology and Computer
PB  - Atlantis Press
SP  - 1018
EP  - 1021
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmebc-16.2016.212
DO  - 10.2991/mmebc-16.2016.212
ID  - Shen2016/06
ER  -