# Named Entity Disambiguation for Noisy Text

## TL;DR

This paper introduces WikilinksNED, a large-scale noisy text dataset for Named Entity Disambiguation, along with a neural model that effectively handles limited context and noise, outperforming existing methods.

## Contribution

The paper presents a new noisy dataset, a novel sampling method for training, and improved embedding initialization techniques for NED.

## Key findings

- Model outperforms state-of-the-art on WikilinksNED
- Achieves comparable results on newswire datasets
- Introduces a new approach for noisy text NED

## Abstract

We address the task of Named Entity Disambiguation (NED) for noisy text. We present WikilinksNED, a large-scale NED dataset of text fragments from the web, which is significantly noisier and more challenging than existing news-based datasets. To capture the limited and noisy local context surrounding each mention, we design a neural model and train it with a novel method for sampling informative negative examples. We also describe a new way of initializing word and entity embeddings that significantly improves performance. Our model significantly outperforms existing state-of-the-art methods on WikilinksNED while achieving comparable performance on a smaller newswire dataset.