The stages of event extraction

By David Ahn. 2006

592 citations recorded by the source corpus.

Event detection and recognition is a complex task consisting of multiple sub-tasks of varying difficulty. In this paper, we present a simple, modular approach to event extraction that allows us to experiment with a variety of machine learning methods for these sub-tasks, as well as to evaluate the impact on performance these sub-tasks have on the overall task.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/c8687ca5543bf32a9718627df5cd0fcabaacc61c

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. Maosong Sun
3. Kang Liu
4. Jun Zhao
5. Thien Huu Nguyen
6. Yubo Chen
7. Xu Han
8. Heng Ji

In Management Science and Operations Research

1. Yubo Chen
2. Kang Liu
3. Thien Huu Nguyen
4. Ralph Grishman
5. Jian Liu
6. Heng Ji
7. Jun Zhao
8. Zhiyuan Liu

Citations in the corpus

• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, unknown): “Event detection (Grishman, 1997; Chinchor and 016 Marsh, 1998; Ahn, 2006) is the task of identifying 017 and typing event mentions from natural language 018 text.”
• MAVEN: A Massive General Domain Event Detection Dataset (2020, methodology): “ED is the first stage to extract event knowledge from text (Ahn, 2006) and also fundamental to various Preprint.”
• Using Document Level Cross-Event Inference to Improve Event Extraction (2010, background): “Almost all the current ACE event extraction systems focus on processing one sentence at a time (Grishman et al., 2005; Ahn, 2006; Hardy et al. 2006).”
• 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.”
• Refining Event Extraction through Cross-Document Inference (2008, background): “Almost all the current event extraction systems focus on processing single documents and, except for coreference resolution, operate a sentence at a time (Grishman et al., 2005; Ahn, 2006; Hardy et al., 2006).”
• Graph Convolutional Networks With Argument-Aware Pooling for Event Detection (2018, methodology): “Note that the governor and dependent words has also been found as useful features for ED in the traditional feature approaches (Ahn 2006; Li, Ji, and Huang 2013).”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, unknown): “Event extraction (Grishman, 1997; Chinchor and 025 Marsh, 1998; Ahn, 2006) is a task to identify and 026 type event triggers and participants from natural 027 language text.”
• 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”
• Incremental Event Detection via Knowledge Consolidation Networks (2020, methodology): “Ahn (2006) leverage lexical features, syntactic features and external knowledge features to extract the event.”
• Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks (2015, background): “Ahn (2006) uses the lexical features(e.g., full word, pos tag), syntactic features (e.g., dependency features) and external-knowledge features(WordNet) to extract the event.”
• A language-independent neural network for event detection (2016, unknown): “The majority of the existing methods regard this problem as a classification task and use machine learning methods with hand-crafted features, such as lexical (e.g., full word, pos tag), syntactic (e.g., dependency features) and external knowledge (WordNet) features [21].”
• Joint Event Extraction via Structured Prediction with Global Features (2013, background): “…about ACE event extraction rely on staged pipeline which consists of separate local classifiers for trigger labeling and argument labeling (Grishman et al., 2005; Ahn, 2006; Ji and Grishman, 2008; Chen and Ji, 2009; Liao and Gr-ishman, 2010; Hong et al., 2011; Li et al., 2012a; Chen and Ng, 2012).”
• Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection (2019, background): “Feature-based approaches include (Ahn 2006) that examined lexical and syntactic features; (Ji and Grishman 2008; Hong et al. 2011; Li, Ji, and Huang 2013) that examined both local and global features and others.”
• Joint Event Extraction via Recurrent Neural Networks (2016, background): “Early research on event extraction has primarily focused on local sentence-level representations in a pipelined architecture (Grishman et al., 2005; Ahn, 2006).”