Abstract | ||
---|---|---|
Entity linking, the task of mapping textual mentions to known entities, has recently been tackled using contextualized neural networks. We address the question whether these results — reported for large, high-quality datasets such as Wikipedia — transfer to practical business use cases, where labels are scarce, text is low-quality, and terminology is highly domain-specific.Using an entity linking model based on BERT, a popular transformer network in natural language processing, we show that a neural approach outperforms and complements hand-coded heuristics, with improvements of about 20% top-1 accuracy. Also, the benefits of transfer learning on a large corpus are demonstrated, while fine-tuning proves difficult. Finally, we compare different BERT-based architectures and show that a simple sentence-wise encoding (Bi-Encoder) offers a fast yet efficient search in practice. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/SDS49233.2020.00014 | 2020 7th Swiss Conference on Data Science (SDS) |
Keywords | DocType | ISBN |
Entity Linking,Attention Models,Natural Language Processing | Conference | 978-1-7281-7177-7 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kurz Nadja | 1 | 0 | 0.34 |
Hamann Felix | 2 | 0 | 0.34 |
Adrian Ulges | 3 | 328 | 26.61 |