Entity Candidate Network for Whole-Aware Named Entity Recognition
This work addresses limitations in traditional NER methods for downstream NLP tasks like coreference resolution by offering a regulable approach between precision and recall, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of Named Entity Recognition (NER) by proposing a no-tag scheme called Whole-Aware Detection, which treats NER as an object detection task, and introduces the Entity Candidate Network (ECNet) model; experimental results show that ECNet outperforms previous state-of-the-art methods on the CoNLL 2003 English and WNUT 2017 datasets.
Named Entity Recognition (NER) is a crucial upstream task in Natural Language Processing (NLP). Traditional tag scheme approaches offer a single recognition that does not meet the needs of many downstream tasks such as coreference resolution. Meanwhile, Tag scheme approaches ignore the continuity of entities. Inspired by one-stage object detection models in computer vision (CV), this paper proposes a new no-tag scheme, the Whole-Aware Detection, which makes NER an object detection task. Meanwhile, this paper presents a novel model, Entity Candidate Network (ECNet), and a specific convolution network, Adaptive Context Convolution Network (ACCN), to fuse multi-scale contexts and encode entity information at each position. ECNet identifies the full span of a named entity and its type at each position based on Entity Loss. Furthermore, ECNet is regulable between the highest precision and the highest recall, while the tag scheme approaches are not. Experimental results on the CoNLL 2003 English dataset and the WNUT 2017 dataset show that ECNet outperforms other previous state-of-the-art methods.