Joint Event Extraction via Recurrent Neural Networks
Explore this paper's citation graph
Summary
This work proposes to do event extraction in a joint framework with bidirectional recurrent neural networks, thereby benefiting from the advantages of the two models as well as addressing issues inherent in the existing approaches.
- Type
- article
- Published
- 2016-06-01
- Cited by
- 652
- References
- 36
- Access
- Open access
- OpenAlex
- https://openalex.org/W2475245295
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:6452487
Keywords
Computer science, Joint (building), Event (particle physics), Artificial intelligence, Extraction (chemistry)
References
- ADADELTA: An Adaptive Learning Rate Method
- Robust Biomedical Event Extraction with Dual Decomposition and Minimal Domain Adaptation
- An Empirical Exploration of Recurrent Network Architectures
- Efficient Estimation of Word Representations in Vector Space
- Convolutional Neural Networks for Sentence Classification
- Fast and Robust Joint Models for Biomedical Event Extraction
- Joint Inference for Knowledge Extraction from Biomedical Literature
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- A Markov Logic Approach to Bio-Molecular Event Extraction
- Long short-term memory in recurrent neural networks
- Long Short-Term Memory
- The stages of event extraction
- Event Extraction as Dependency Parsing
- Learning long-term dependencies with gradient descent is difficult
- Using Document Level Cross-Event Inference to Improve Event Extraction
- A unified architecture for natural language processing: deep neural networks with multitask learning
- Predicting Unknown Time Arguments based on Cross-Event Propagation
- Using Cross-Entity Inference to Improve Event Extraction
- A Unified Model of Phrasal and Sentential Evidence for Information Extraction
- Distributed Representations of Words and Phrases and their Compositionality
Cited by
- A Two-stage Approach for Extending Event Detection to New Types via Neural Networks
- Information Extraction with Character-level Neural Networks and Noisy Supervision
- Modeling Skip-Grams for Event Detection with Convolutional Neural Networks
- Incremental Global Event Extraction
- Joint Learning of Local and Global Features for Entity Linking via Neural Networks
- Automatically Labeled Data Generation for Large Scale Event Extraction
- End-to-End Information Extraction without Token-Level Supervision
- Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms
- Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
- Leveraging Knowledge Bases in LSTMs for Improving Machine Reading
- A Neural Model for Joint Event Detection and Summarization
- Représentations et modèles en extraction d'événements supervisée
- Unsupervised Event Clustering and Aggregation from Newswire and Web Articles
- Boosting Information Extraction Systems with Character-level Neural Networks and Free Noisy Supervision
- Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators
- Supervised algorithms for complex relation extraction
- Improving Event Extraction via Multimodal Integration
- Scale Up Event Extraction Learning via Automatic Training Data Generation
- Event Argument Identification on Dependency Graphs with Bidirectional LSTMs
- Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging
Related papers
- A Study on Performance Improvement of Recurrent Neural Networks Algorithm using Word Group Expansion Technique
- Fusion Recurrent Neural Network
- Gated Feedback Recurrent Neural Networks
- Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network
- How to Construct Deep Recurrent Neural Networks
- How to Construct Deep Recurrent Neural Networks