Robust Lexical Features for Improved Neural Network Named-Entity Recognition
arXiv:1806.03489
Abstract
Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features. While some features do remain in state-of-the-art systems, lexical features have been mostly discarded, with the exception of gazetteers. In this work, we show that this is unfair: lexical features are actually quite useful. We propose to embed words and entity types into a low-dimensional vector space we train from annotated data produced by distant supervision thanks to Wikipedia. From this, we compute - offline - a feature vector representing each word. When used with a vanilla recurrent neural network model, this representation yields substantial improvements. We establish a new state-of-the-art F1 score of 87.95 on ONTONOTES 5.0, while matching state-of-the-art performance with a F1 score of 91.73 on the over-studied CONLL-2003 dataset.
arXiv comment12 pages, to appear in COLING 2018
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- ADADELTA: An Adaptive Learning Rate Method
- Natural Language Processing (almost) from Scratch
- Exploring the Limits of Language Modeling
- Enriching Word Vectors with Subword Information
- End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
- Deep Active Learning for Named Entity Recognition
- Named Entity Recognition with stack residual LSTM and trainable bias decoding
Cited by in corpus (6)
- TENER: Adapting Transformer Encoder for Named Entity Recognition
- A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
- Sentence, Phrase, and Triple Annotations to Build a Knowledge Graph of Natural Language Processing Contributions -- A Trial Dataset
- Korean Named Entity Recognition Based on Language-Specific Features
- SpanNER: Named Entity Re-/Recognition as Span Prediction
- Larger-Context Tagging: When and Why Does It Work?