Chinese Event Extraction Based on Attention and Semantic Features: A Bidirectional Circular Neural Network
Explore this paper's citation graph
Summary
A novel architecture for combining word representations: character–word embedding based on attention and semantic features is proposed, and this method is found to improve performance.
- Type
- article
- Published
- 2018-09-26
- Cited by
- 8
- References
- 20
- Access
- Open access
- OpenAlex
- https://openalex.org/W2894444728
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:53225346
Keywords
Computer science, Word (group theory), Character (mathematics), Artificial intelligence, Natural language processing
References
- Event Recognition Based on Deep Learning in Chinese Texts
- Efficient Estimation of Word Representations in Vector Space
- Chinese Event Extraction Based on Feature Weighting
- A maximum entropy approach to information extraction from semi-structured and free text
- Long Short-Term Memory
- The stages of event extraction
- Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
- Using Document Level Cross-Event Inference to Improve Event Extraction
- Refining Event Extraction through Cross-Document Inference
- Joint Event Extraction via Structured Prediction with Global Features
- Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
- Joint Learning of Character and Word Embeddings
- The Automatic Content Extraction (ACE) Program – Tasks, Data, and Evaluation
- Joint Event Extraction via Recurrent Neural Networks
- Extracting Knowledge from the Geometric Shape of Social Network Data Using Topological Data Analysis
- Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition
- Segment-Level Neural Conditional Random Fields for Named Entity Recognition
Cited by
- Environmental Hazards: A Coverage Response Approach
- Chinese Event Detection Based on Multi-Feature Fusion and BiLSTM
- A Survey of Event Extraction From Text
- Automatic work‐order assignment method for Chinese government hotline
- Chinese Event Extraction Method based on Abstract Meaning Representation Graph
- Chinese Event Extraction Method Based on Word Feature and Pointer Network
- CED-BGFN: Chinese Event Detection via Bidirectional Glyph-Aware Dynamic Fusion Network
- Character-Based LSTM-CRF with Semantic Features for Chinese Event Element Recognition
Related papers
- How to Generate a Good Word Embedding
- Deconstructing Word Embeddings
- Dual embedding with input embedding and output embedding for better word representation
- NMT Multi-Sense Embeddings per Word
- Multi-Sense Embeddings per Word
- Synergistic Union of Word Embedding and Knowledge Graph for Words Semantic Similarity Measure
- Towards the Importance of the Type of Deep Neural Network and Employment of Pre-trained Word Vectors for Toxicity Detection: An Experimental Study
- ArSphere: Arabic word vectors embedded in a polar sphere