Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms

By Shulin Liu, Yubo Chen, Kang Liu, Jun Zhao. 2017

225 citations recorded by the source corpus.

This paper tackles the task of event detection (ED), which involves identifying and categorizing events. We argue that arguments provide significant clues to this task, but they are either completely ignored or exploited in an indirect manner in existing detection approaches. In this work, we propose to exploit argument information explicitly for ED via supervised attention mechanisms. In specific, we systematically investigate the proposed model under the supervision of different attention strategies. Experimental results show that our approach advances state-of-the-arts and achieves the best F1 score on ACE 2005 dataset.

Subfields: Artificial Intelligence, Natural Language Processing

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. Graham Neubig
3. Maosong Sun
4. Mo Yu
5. Pengfei Liu
6. Kang Liu
7. Xu Han
8. Heng Ji

In Natural Language Processing

1. Graham Neubig
2. Pengfei Liu
3. Zhiyuan Liu
4. Jinlan Fu
5. Weizhe Yuan
6. Heng Ji
7. Dichao Hu
8. Mo Yu

Citations in the corpus

• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2021, background): “Supervised attention [76] aims to provide explicit supervision over the attention of models based on the fact that completely data-driven attention can overit to some artifacts [73].”
• Fine-grained Sentiment Analysis with Faithful Attention (2019, methodology): “For instance, Mi et al. (2016) used word alignment to guide machine translation and Liu et al. (2017) used argument keywords to improve event detection.”
• Deriving Machine Attention from Human Rationales (2018, methodology): “…using word alignments to learn attention in neural machine translation (Liu et al., 2016), employing argu-ment words to supervise attention in event detection (Liu et al., 2017), utilizing linguistically-motivated annotations to guide attention in constituency parsing (Kamigaito et al., 2017).”
• Few-Shot Semantic Parsing for New Predicates (2021, background): “, 2017), or it is designed only for applications other than semantic parsing (Liu et al., 2017; Kamigaito et al., 2017).”
• Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation (2018, unknown): “• The positional embedding vector of w i : If w c is the current word, we encode the relative distance i − c from w i to w c as a real-valued vector by looking up the randomly initialized position embedding table (Nguyen et al., 2016; Liu et al., 2017; Nguyen and Gr-ishman, 2018).”
• Graph Convolutional Networks With Argument-Aware Pooling for Event Detection (2018, background): “Syntactic dependency graphs represents sentences as directed trees with head-modifier dependency arcs between related words (Mcdonald and Pereira 2006; Koo, Carreras, and Collins 2008).”
• Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection (2019, methodology): “Previous studies have shown that the chunk knowledge corresponding to the sentences can provide evidence for event type disambiguation (Hong et al. 2011; Li, Ji, and Huang 2013; Feng et al. 2016; Liu et al. 2017).”
• Lifelong Event Detection with Knowledge Transfer (2021, methodology): “Event detection under the traditional setting has been widely studied (Ji and Grishman, 2008; Chen et al., 2015; Feng et al., 2016; Liu et al., 2017, 2018, 2019; Lu et al., 2019; Ding et al., 2019; Yan et al., 2019; Tong et al., 2020).”
• An Introductory Survey on Attention Mechanisms in NLP Problems (2018, methodology): “Similarly, Liu et al. proposed a method to manually construct ”gold attention vec-tors” (Liu et al. 2017) by first identifying labelled key words within a sentence and then conducting post-processing procedures such as smoothing and normalization, given abundant well-annotated data.”
• Incremental Event Detection via Knowledge Consolidation Networks (2020, methodology): “The proposed models can be divided into feature-based methods (Ahn, 2006; Ji and Grishman, 2008; Liao and Grishman, 2010; Li et al., 2013; Li and Ji, 2014) and neural network-based methods (Chen et al., 2015; Nguyen and Grishman, 2015; Liu et al., 2017, 2018a,b; Lu et al., 2019; Ding et al., 2019).”
• Exploring Pre-trained Language Models for Event Extraction and Generation (2019, methodology): “While Liu et al. (2016, 2017) manages to mine additional events from the frames in FrameNet.”
• MAVEN: A Massive General Domain Event Detection Dataset (2020, background): “…2008; Gupta and Ji, 2009; Li et al., 2013; Araki and Mitamura, 2015) and advanced neural models (Chen et al., 2015; Nguyen and Gr-ishman, 2015; Nguyen et al., 2016; Feng et al., 2016; Ghaeini et al., 2016; Liu et al., 2017; Zhao et al., 2018; Chen et al., 2018; Ding et al., 2019; Yan et al., 2019).”