Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding
arXiv:2109.01636
Abstract
With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even when types of NE and documents are unfamiliar. Realizing that the specificity information may contain potential meanings of a word and generate semantic-related features for word embedding, we develop a distribution-aware word embedding and implement three different methods to make use of the distribution information in a NER framework. And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.
arXiv commentWant to correct
References in corpus (13)
- Distributed Representations of Words and Phrases and their Compositionality
- Natural Language Processing (almost) from Scratch
- A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
- End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
- Word Representations via Gaussian Embedding
- Discriminative Topic Mining via Category-Name Guided Text Embedding
- Spherical Text Embedding
- Deep Active Learning for Named Entity Recognition
- Embedding Words as Distributions with a Bayesian Skip-gram Model
- Robust Named Entity Recognition with Truecasing Pretraining
- Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
- CrossWeigh: Training Named Entity Tagger from Imperfect Annotations
- Raw-to-End Name Entity Recognition in Social Media