Work

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

Year: 2020

Type: conference-paper

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%.

Source: International Conference on Computational Linguistics

DOI: 10.18653/v1/2020.coling-main.411

Authors: Hao Zhang, Jae Ro, Richard Sproat

Institution: Google (United States)

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W3106295233

FWCI: 0.572

Cites: 21

Cited by: 6

Related to: 10