Neural Reranking for Named Entity Recognition
This work addresses the challenge of improving NER accuracy for natural language processing applications, representing an incremental advancement through reranking techniques.
The paper tackles the problem of named entity recognition by proposing a neural reranking system that uses LSTM and CNN models to learn sentence-level patterns from entity types, achieving the best reported results on a standard benchmark with significant accuracy improvements over two baselines.
We propose a neural reranking system for named entity recognition (NER). The basic idea is to leverage recurrent neural network models to learn sentence-level patterns that involve named entity mentions. In particular, given an output sentence produced by a baseline NER model, we replace all entity mentions, such as \textit{Barack Obama}, into their entity types, such as \textit{PER}. The resulting sentence patterns contain direct output information, yet is less sparse without specific named entities. For example, "PER was born in LOC" can be such a pattern. LSTM and CNN structures are utilised for learning deep representations of such sentences for reranking. Results show that our system can significantly improve the NER accuracies over two different baselines, giving the best reported results on a standard benchmark.