• Corpus ID: 248512779

DEGREE: A Data-Efficient Generation-Based Event Extraction Model

  title={DEGREE: A Data-Efficient Generation-Based Event Extraction Model},
  author={I-Hung Hsu and Kuan-Hao Huang and Elizabeth Boschee and Scott Miller and Premkumar Natarajan and Kai-Wei Chang and Nanyun Peng},
Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extraction and propose D EGREE , a data-efficient model that for-mulates event extraction as a conditional generation problem. Given a passage and a manually designed prompt, D EGREE learns to summarize… 
A Simple and Unified Tagging Model with Priming for Relational Structure Predictions
This work demonstrates that simple tagging models can surprisingly achieve competitive performances with a small trick — priming, and proposes an efficient approximation to the method, which can perform almost the same performance but with faster inference speed.


Exploring Pre-trained Language Models for Event Extraction and Generation
This work proposes an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles, and proposes a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality.
Document-Level Event Argument Extraction by Conditional Generation
A document-level neural event argument extraction model is proposed by formulating the task as conditional generation following event templates by creating the first end-to-end zero-shot event extraction framework.
Event Extraction as Machine Reading Comprehension
This paper proposes a new learning paradigm of EE, by explicitly casting it as a machine reading comprehension problem (MRC), which includes an unsupervised question generation process, which can transfer event schema into a set of natural questions, followed by a BERT-based question-answering process to retrieve answers as EE results.
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction
Experimental results show that, by uniformly modeling all tasks in a single model and universally predicting different labels, the Text2Event method can achieve competitive performance using only record-level annotations in both supervised learning and transfer learning settings.
One for All: Neural Joint Modeling of Entities and Events
This work proposes a novel model to jointly perform predictions for entity mentions, event triggers and arguments based on the shared hidden representations from deep learning, leading to the state-of-the-art performance for event extraction.
A Joint Neural Model for Information Extraction with Global Features
A joint neural framework that aims to extract the globally optimal IE result as a graph from an input sentence and can be easily applied to new languages or trained in a multilingual manner, as OneIE does not use any language-specific feature.
Event Extraction as Multi-turn Question Answering
This work proposes a new paradigm that formulates event extraction as multi-turn question answering, MQAEE, which makes full use of dependency among arguments and event types, and generalizes well to new types with new argument roles.
Joint Event Extraction via Structured Prediction with Global Features
This work proposes a joint framework based on structured prediction which extracts triggers and arguments together so that the local predictions can be mutually improved, and proposes to incorporate global features which explicitly capture the dependencies of multiple triggers and argued.
Entity, Relation, and Event Extraction with Contextualized Span Representations
This work examines the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction (called DyGIE++) and achieves state-of-the-art results across all tasks.
Joint Event Extraction via Recurrent Neural Networks
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.