A Multi-task Learning Approach for Named Entity Recognition using Local Detection
This work addresses the data scarcity issue in NER for NLP researchers, but it is incremental as it builds on existing multi-task learning methods.
The paper tackled the problem of limited annotated data for named entity recognition (NER) by combining existing datasets with a multi-task learning approach, achieving competitive performance across several well-known NER tasks.
Named entity recognition (NER) systems that perform well require task-related and manually annotated datasets. However, they are expensive to develop, and are thus limited in size. As there already exists a large number of NER datasets that share a certain degree of relationship but differ in content, it is important to explore the question of whether such datasets can be combined as a simple method for improving NER performance. To investigate this, we developed a novel locally detecting multitask model using FFNNs. The model relies on encoding variable-length sequences of words into theoretically lossless and unique fixed-size representations. We applied this method to several well-known NER tasks and compared the results of our model to baseline models as well as other published results. As a result, we observed competitive performance in nearly all of the tasks.