Named Entity Recognition Only from Word Embeddings
arXiv:1909.00164
Abstract
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.
arXiv commentAccepted by EMNLP2020
References in corpus (7)
- Natural Language Processing (almost) from Scratch
- Reinforcement Learning for Relation Classification from Noisy Data
- Design Challenges and Misconceptions in Neural Sequence Labeling
- Empower Sequence Labeling with Task-Aware Neural Language Model
- SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data
- Unsupervised POS Induction with Word Embeddings
- A Hidden Markov Model Based System for Entity Extraction from Social Media English Text at FIRE 2015