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

arXiv: https://arxiv.org/abs/2011.03138 · HTML: https://mlsanity.com/paper/2011.03138/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models](https://mlsanity.com/paper/2203.06904/) (2022)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [Exploring Universal Intrinsic Task Subspace via Prompt Tuning](https://mlsanity.com/paper/2110.07867/) (2021)
- [Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts](https://mlsanity.com/paper/2205.12701/) (2022)
- [Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?](https://mlsanity.com/paper/2302.08143/) (2023)
- [SkyLadder: Better and Faster Pretraining via Context Window Scheduling](https://mlsanity.com/paper/2503.15450/) (2025)
- [Transformer-based Models of Text Normalization for Speech Applications](https://mlsanity.com/paper/2202.00153/) (2022)
- [Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning](https://mlsanity.com/paper/2312.17055/) (2023)
- [Non-Standard Vietnamese Word Detection and Normalization for Text-to-Speech](https://mlsanity.com/paper/2209.02971/) (2022)
- [Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection](https://mlsanity.com/paper/2401.12326/) (2024)
- [Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning](https://mlsanity.com/paper/2210.13311/) (2022)

## Abstract (arXiv)

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%.