Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation

By Xiao Liu, Zhunchen Luo, Heyan Huang. Conference on Empirical Methods in Natural Language Processing, 2018

372 citations recorded by the source corpus.

Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6f0637f44ac481905d732be7a2e15d8f699aeeb3

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. Zhiyuan Liu
2. Heng Ji
3. Maosong Sun
4. Xu Han
5. Yankai Lin
6. Peng Li
7. Kang Liu
8. Jie Zhou

Citations in the corpus

• Graph convolutional networks: a comprehensive review (2019, positive): “Graph convolutional networks have been designed to the relation extraction between words [100, 101] and event extraction [102, 103].”
• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, background): “…2020; Zhang et al., 2020c), 2) multi-task joint models (McClosky et al., 2011; Li et al., 2013, 2014; Yang and Mitchell, 2016; Nguyen et al., 2016; Liu et al., 2018; Zhang et al., 2019a; Zheng et al., 2019), 3) semantic structure grounding (Huang et al., 2016, 2018; Zhang et al., 2020a), and 4)…”
• Event Extraction as Machine Reading Comprehension (2020, methodology): “…Neural Networks (Chen et al., 2015), Recurrent Neural Networks (Nguyen et al., 2016; Sha et al., 2018), Graph Convolutional Neural Networks (Liu et al., 2018b, 2019b), and other advanced architectures (Yang and Mitchell, 2016; Liu et al., 2018a, 2019a; Nguyen and Nguyen, 2019; Zhang et…”
• MAVEN: A Massive General Domain Event Detection Dataset (2020, background): “Chen et al., 2018; Liu et al., 2018) on ACE 2005 dataset, we observe that this phenomenon is much more common and complex on MAVEN.”
• Semi-supervised New Event Type Induction and Event Detection (2020, background): “Traditional event extraction studies (Ji and Grishman, 2008; McClosky et al., 2011; Li et al., 2013; Chen et al., 2015; Yang and Mitchell, 2016; Liu et al., 2018; Nguyen and Nguyen, 2019; Lin et al., 2020; Li et al., 2020) usually assume there exists a set of predefined event types and argument role”
• Event Extraction by Answering (Almost) Natural Questions (2020, background): “Nguyen et al., 2016; Liu et al., 2018) and contex-tualized representations from pretrained language models (Zhang et al., 2019b; Wadden et al., 2019).”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, neutral): “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…”