Using Document Level Cross-Event Inference to Improve Event Extraction

By Shasha Liao, Ralph Grishman. Annual Meeting of the Association for Computational Linguistics, 2010

360 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/639598a428b667cb4573cc3688c1e8b3f3d667b7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Thien Huu Nguyen
2. Yubo Chen
3. Jian Liu
4. Mo Yu
5. Kang Liu
6. Ralph Grishman
7. Yoav Goldberg
8. Heng Ji

Citations in the corpus

• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, methodology): “Supervised Event Detection: Most of the existing Event Detection studies follow a supervised learning paradigm (Ji and Grishman, 2008; Liao and Grishman, 2010; McClosky et al., 2011; Li et al., 2013; Chen et al., 2015; Cao et al., 2015; Feng et al., 2016; Yang and Mitchell, 2016; Nguyen et al.,…”
• Joint Event Extraction via Recurrent Neural Networks (2016, methodology): “Also, we follow the criteria of the previous work (Ji and Grishman, 2008; Liao and Grishman, 2010; Li et al., 2013; Chen et al., 2015) to judge the correctness of the predicted event mentions.”
• Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks (2015, methodology): “For comparison, as the same as Li et al. (2013), Hong et al. (2011) and Liao and Grishman (2010), we used the same test set with 40 newswire articles and the same development set with 30 other documents randomly selected from different genres and the rest 529 documents are used for training.”
• Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation (2018, methodology): “We compare our performance with the following state-of-the-art methods: 1 Cross-Event is proposed by Liao and Grishman (2010), which uses document level information to improve the performance of event extraction; 2 JointBeam is the method proposed by Li et al. (2013), which extracts events based on…”
• Seed-Based Event Trigger Labeling: How far can event descriptions get us? (2015, methodology): “Most state-of-the-art event trigger labeling approaches (Ji and Grishman, 2008; Liao and Grishman, 2010b; Hong et al., 2011; Li et al., 2013) follow the standard supervised learning paradigm.”
• Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms (2017, background): “, POS tags, dependency relations) into feature vectors (Ahn, 2006; Ji and Grishman, 2008; Patwardhan and Riloff, 2009; Gupta and Ji, 2009; Liao and Grishman, 2010; Hong et al., 2011; Liu et al., 2016b).”
• Richer Event Description: Integrating event coreference with temporal, causal and bridging annotation (2016, background): “Rich interactions between events in a text, moreover, may be useful for a wide range of goals; Liao and Grishman (2010) found that looking at related events within a document could aid ACE-style event detection, and Vossen et al. (2015) discussed the value of combining time-lines with bridging and…”
• Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021, methodology): “These methods can be divided into: 1) pipeline classification (Ahn, 2006; Ji 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”
• Joint Event Extraction via Structured Prediction with Global Features (2013, methodology): “For comparison, we used the same test set with 40 newswire articles (672 sentences) as in (Ji and Grishman, 2008; Liao and Grishman, 2010) for the experiments, and randomly selected 30 other documents (863 sentences) from different genres as the development set.”
• Exploring Pre-trained Language Models for Event Extraction and Generation (2019, methodology): “We take several previous classic works for comparison, and divide them into three categories: Feature based methods Document-level information is utilized in Cross event (Liao and Grishman, 2010) to assist event extraction.”
• Event Detection and Domain Adaptation with Convolutional Neural Networks (2015, result): “(672 sentences), the same development set with 30 other documents (836 sentences) and the same training set with the remaning 529 documents (14,849 sentences) as the previous studies on this dataset (Ji and Grishman, 2008; Liao and Grishman, 2010; Li et al., 2013b).”
• 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).”
• Event Extraction as Machine Reading Comprehension (2020, methodology): “Traditional EE methods employ manual-designed features, such as the syntactic feature (Ahn, 2006), document-level feature (Ji and Grishman, 2008), entity-level feature (Hong et al., 2011) and other features (Liao and Grishman, 2010; Li et al., 2013) Figure 2: The overview of the proposed model RCEE.”
• Improving Event Extraction via Multimodal Integration (2017, background): “In order to acquire a deeper understanding of the content, Event Extraction (EE) techniques have been developed to automatically extract information units, such as “ what is happening ” and “ who, or what, is involved ” [19, 24, 26], in a precise, clear, and structured form.”