Exploring Pre-trained Language Models for Event Extraction and Generation

By Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, Dongsheng Li. Annual Meeting of the Association for Computational Linguistics, 2019

341 citations recorded by the source corpus.

Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size. Therefore, in addition to the difficulty of event extraction itself, insufficient training data hinders the learning process as well. To promote event extraction, we first propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles. Moreover, to address the problem of insufficient training data, we propose a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality. Experiments on the ACE2005 dataset demonstrate that our extraction model can surpass most existing extraction methods. Besides, incorporating our generation method exhibits further significant improvement. It obtains new state-of-the-art results on the event extraction task, including pushing the F1 score of trigger classification to 81.1%, and the F1 score of argument classification to 58.9%.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/36b79362d2927824e0daa864dd32cf0de7ca35f9

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

1. Yubo Chen
2. Jun Zhao
3. Taifeng Wang
4. Pengfei Cao
5. Chao Zhang
6. Yue Yu
7. Rongzhi Zhang
8. Zhiyuan Liu

Citations in the corpus

• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, neutral): “…and Grishman, 2008; Liao and Grishman, 2010; Hong et al., 2011, 2018; Huang and Riloff, 2012; Chen et al., 2015; Sha et al., 2016; Lin et al., 2018; Yang et al., 2019; Wang et al., 2019; Ma et al., 2020; Zhang et al., 2020c), 2) multi-task joint models (McClosky et al., 2011; Li et al., 2013,…”
• Incremental Event Detection via Knowledge Consolidation Networks (2020, background): “BERT is a multi-layer bidirectional Transformer, pre-trained on a large-scale unlabeled corpus, which has achieved the state-of-the-art performance for event detection (Wang et al., 2019b; Yang et al., 2019).”
• SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup (2020, background): “Many NLP tasks can be formulated as sequence labeling problems, such as part-of-speech (POS) tagging (Zheng et al., 2013), named entity recognition (NER) (Lample et al., 2016), and event extraction (Yang et al., 2019).”