TENER: Adapting Transformer Encoder for Named Entity Recognition
This addresses a specific bottleneck in NER for NLP researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackled the underperformance of Transformer models in Named Entity Recognition (NER) by proposing TENER, an adapted Transformer encoder that incorporates direction and relative distance aware attention and un-scaled attention, achieving competitive performance comparable to other NLP tasks.
The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task. Recently, the Transformer is broadly adopted in various Natural Language Processing (NLP) tasks owing to its parallelism and advantageous performance. Nevertheless, the performance of the Transformer in NER is not as good as it is in other NLP tasks. In this paper, we propose TENER, a NER architecture adopting adapted Transformer Encoder to model the character-level features and word-level features. By incorporating the direction and relative distance aware attention and the un-scaled attention, we prove the Transformer-like encoder is just as effective for NER as other NLP tasks.