Back to Search
Start Over
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
- Source :
- ACL/IJCNLP (1)
- Publication Year :
- 2021
-
Abstract
- Event extraction is challenging due to the complex structure of event records and the semantic gap between text and event. Traditional methods usually extract event records by decomposing the complex structure prediction task into multiple subtasks. In this paper, we propose Text2Event, a sequence-to-structure generation paradigm that can directly extract events from the text in an end-to-end manner. Specifically, we design a sequence-to-structure network for unified event extraction, a constrained decoding algorithm for event knowledge injection during inference, and a curriculum learning algorithm for efficient model learning. Experimental results show that, by uniformly modeling all tasks in a single model and universally predicting different labels, our method can achieve competitive performance using only record-level annotations in both supervised learning and transfer learning settings.<br />Accepted to ACL2021 (main conference)
- Subjects :
- Structure (mathematical logic)
FOS: Computer and information sciences
Computer Science - Computation and Language
business.industry
Event (computing)
Computer science
Supervised learning
Inference
Machine learning
computer.software_genre
Task (project management)
Artificial intelligence
business
Transfer of learning
computer
Computation and Language (cs.CL)
Decoding methods
Semantic gap
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- ACL/IJCNLP (1)
- Accession number :
- edsair.doi.dedup.....357bdd1eca94f3b4da12a212b37ee060