Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities

Hao Zhang, Jae Ro, Richard Sproat


Abstract
Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search. We link this problem to the classic problem of Chinese word segmentation and show the effectiveness of a tagging model based on Recurrent Neural Networks (RNNs) using characters as input. To compensate for the lack of training data, we propose a pre-training method on concatenated entity names in a large knowledge database. Pre-training improves the model by 33% and brings the sequence accuracy to 85%.
Anthology ID:
2020.coling-main.411
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4667–4675
Language:
URL:
https://aclanthology.org/2020.coling-main.411
DOI:
10.18653/v1/2020.coling-main.411
Bibkey:
Cite (ACL):
Hao Zhang, Jae Ro, and Richard Sproat. 2020. Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4667–4675, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities (Zhang et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.411.pdf
Code
 google-research-datasets/common-crawl-domain-names