HAMNER: Headword Amplified Multi-span Distantly Supervised Method for Domain Specific Named Entity Recognition
This addresses the problem of labor-intensive data annotation for NER in specific domains, though it is an incremental improvement over existing distantly supervised methods.
The paper tackles the limited coverage of dictionaries in distantly supervised Named Entity Recognition (NER) by extending dictionaries with headword-based non-exact matching and using a span-level model with dynamic programming, achieving state-of-the-art performance on three benchmark datasets.
To tackle Named Entity Recognition (NER) tasks, supervised methods need to obtain sufficient cleanly annotated data, which is labor and time consuming. On the contrary, distantly supervised methods acquire automatically annotated data using dictionaries to alleviate this requirement. Unfortunately, dictionaries hinder the effectiveness of distantly supervised methods for NER due to its limited coverage, especially in specific domains. In this paper, we aim at the limitations of the dictionary usage and mention boundary detection. We generalize the distant supervision by extending the dictionary with headword based non-exact matching. We apply a function to better weight the matched entity mentions. We propose a span-level model, which classifies all the possible spans then infers the selected spans with a proposed dynamic programming algorithm. Experiments on all three benchmark datasets demonstrate that our method outperforms previous state-of-the-art distantly supervised methods.