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

TL;DR

This paper presents a semi-supervised approach for URL segmentation using RNNs, enhanced by pre-training on knowledge graph entities, achieving significant accuracy improvements for domain name parsing.

Contribution

The paper introduces a novel pre-training method on knowledge graph entities to improve RNN-based URL segmentation, addressing data scarcity issues.

Findings

Pre-training improves model accuracy by 33%.

Sequence accuracy reaches 85%.

Effective segmentation of domain names like openresearch.

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%.