Bi-Lattice LSTM Model with Self-Attention for Chinese NER
- 28 October 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12, 1465-1470
Abstract
In this paper, we investigate a bi-lattice-structured LSTM model for Chinese NER based lattice LSTM model, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with lattice LSTM model, our model fully combines the forward and backward information of each character in the word. And we also introduce the highway model to solve the gradient problem to some extent. In order to capture the global sequence information from multiple subspaces, we introduce the self-attention mechanism. Experiments on various datasets show that our model outperforms both original model and other advanced models without relying on external resources such as dictionaries and multi-task joint training.Keywords
This publication has 18 references indexed in Scilit:
- Applying named entity recognition and co-reference resolution for segmenting English textsProgress in Artificial Intelligence, 2017
- Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition2016
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures2016
- Neural Architectures for Named Entity Recognition2016
- Boosting Named Entity Recognition with Neural Character Embeddings2015
- Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings2015
- Malay Named Entity Recognition Based on Rule-Based ApproachInternational Journal of Machine Learning and Computing, 2014
- Disease Named Entity Recognition by Machine Learning Using Semantic Type of MetathesaurusInternational Journal of Machine Learning and Computing, 2013
- Context Modeling and Measuring for Context Aware Knowledge ManagementInternational Journal of Machine Learning and Computing, 2012
- From Text to Knowledge: Semantic Entity Extractionusing YAGO OntologyInternational Journal of Machine Learning and Computing, 2011