Named Entity Recognition Only from Word Embeddings
This work addresses the challenge of reducing annotation costs for named entity recognition, which is important for NLP applications, but it is incremental as it builds on existing unsupervised techniques.
The authors tackled the problem of named entity recognition without requiring human-annotated data or external resources by developing a fully unsupervised model that uses only pre-trained word embeddings. Their model achieved remarkable performance on CoNLL benchmark datasets, demonstrating effectiveness without annotated lexicons or corpora.
Deep neural network models have helped named entity (NE) recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings. We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and refine these coarse-grained annotations through neural networks. Extensive experiments on CoNLL benchmark datasets demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.