Event Extraction as Machine Reading Comprehension
By Jian Liu, Yubo Chen, Kang Liu, Wei Bi, Xiaojiang Liu. Conference on Empirical Methods in Natural Language Processing, 2020
334 citations recorded by the source corpus.
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Previous methods for EE typically model it as a classification task, which are usually prone to the data scarcity problem. In this paper, we propose a new learning paradigm of EE, by explicitly casting it as a machine reading comprehension problem (MRC). Our approach 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. This learning paradigm enables us to strengthen the reasoning process of EE, by introducing sophisticated models in MRC, and relieve the data scarcity problem, by introducing the large-scale datasets in MRC. The empirical results show that: i) our approach attains state-of-the-art performance by considerable margins over previous methods. ii) Our model is excelled in the data-scarce scenario, for example, obtaining 49.8\% in F1 for event argument extraction with only 1\% data, compared with 2.2\% of the previous method. iii) Our model also fits with zero-shot scenarios, achieving $37.0\%$ and $16\%$ in F1 on two datasets without using any EE training data.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/707eb268a60d47b18552f8fe2b0629ba6836617d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, methodology): “Though studies (Yang and Mitchell, 2016; 359 Liu et al., 2020, 2018; Sha et al., 2018; Lai et al., 360 2020; Veyseh et al., 2020) have been conducted 361 on the ACE dataset, they follow different set- 362 tings8, especially regarding whether the Time and 363 Value arguments are considered and…”
- The Art of Prompting: Event Detection based on Type Specific Prompts (2022, background): “…the semantics of event types based on various forms of prompts, such as event type specific queries (Lyu et al., 2021; Du and Cardie, 2020; Liu et al., 2020), defini-tions (Chen et al., 2020), structures (Lin et al., 2020; Wang et al., 2019), or a few prototype event triggers (Wang and…”
- Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey (2021, methodology): “[108], where monolingual unsupervised MT [87] is used to generate the part of the question that does not depend on the template, translating a descriptive statement into a question-style expression.”