SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres
Not on the map. Why?
Abstract (arXiv)
Event-centric structured prediction involves predicting structured outputs of events. In most NLP cases, event structures are complex with manifold dependency, and it is challenging to effectively represent these complicated structured events. To address these issues, we propose Structured Prediction with Energy-based Event-Centric Hyperspheres (SPEECH). SPEECH models complex dependency among event structured components with energy-based modeling, and represents event classes with simple but effective hyperspheres. Experiments on two unified-annotated event datasets indicate that SPEECH is predominant in event detection and event-relation extraction tasks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 57 references that are in the map. First posted on arXiv 23 May 2023.
Builds on
28 of 57 references.
References · 28
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
- 2022Unified Structure Generation for Universal Information Extractioncited by 220
- 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
- 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
- 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
- 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 103
- 2019Hyperspherical Prototype Networkscited by 85
16 more
- 2021DEGREE: A Data-Efficient Generation-Based Event Extraction Modelcited by 82
- 2022MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extractioncited by 65
- 2015Structured Prediction Energy Networkscited by 59
- 2019Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detectioncited by 54
- 2020Joint Constrained Learning for Event-Event Relation Extractioncited by 53
- 2018One for All: Neural Joint Modeling of Entities and Eventscited by 37
- 2017End-to-End Learning for Structured Prediction Energy Networkscited by 33
- 2021Prototypical Representation Learning for Relation Extractioncited by 33
- 2017Bandit Structured Prediction for Neural Sequence-to-Sequence Learningcited by 31
- 2020Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networkscited by 23
- 2021OntoED: Low-resource Event Detection with Ontology Embeddingcited by 23
- 2020Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extractioncited by 15
- 2021MLBiNet: A Cross-Sentence Collective Event Detection Networkcited by 15
- 2016Structured prediction models for RNN based sequence labeling in clinical textcited by 13
- 2018Learning Approximate Inference Networks for Structured Predictioncited by 13
- 2020Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Taskscited by 12
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.