Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
| Autor: | Meng Liao, Chen Shaoyi, Jin Xu, Le Sun, Xianpei Han, Hongyu Lin, Annan Li, Yaojie Lu, Jialong Tang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
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 |
| Zdroj: | ACL/IJCNLP (1) |
| Popis: | 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. Accepted to ACL2021 (main conference) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|