Seed-Based Event Trigger Labeling: How far can event descriptions get us?

By Ofer Bronstein, Ido Dagan, Qi Li, Heng Ji, Anette Frank. 2015

46 citations recorded by the source corpus.

The task of event trigger labeling is typically addressed in the standard supervised setting: triggers for each target event type are annotated as training data, based on annotation guidelines. We propose an alternative approach, which takes the example trigger terms mentioned in the guidelines as seeds, and then applies an eventindependent similarity-based classifier for trigger labeling. This way we can skip manual annotation for new event types, while requiring only minimal annotated training data for few example events at system setup. Our method is evaluated on the ACE-2005 dataset, achieving 5.7% F1 improvement over a state-of-the-art supervised system which uses the full training data.

Subfields: Artificial Intelligence, Information Systems, 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. Luke S. Zettlemoyer
2. Mohit Bansal
3. Hannaneh Hajishirzi
4. Dan Roth
5. Yejin Choi
6. Percy Liang
7. Caiming Xiong
8. Richard Socher

In Information Systems

1. Omer Levy
2. Luke S. Zettlemoyer
3. Eunsol Choi
4. Mo Yu
5. Shiyu Chang
6. Dan Roth
7. Yangqiu Song
8. Haoruo Peng

In Natural Language Processing

1. Luke S. Zettlemoyer
2. Dan Roth
3. Hannaneh Hajishirzi
4. Mohit Bansal
5. Yejin Choi
6. Percy Liang
7. Eunsol Choi
8. Omer Levy

Citations in the corpus

• Zero-Shot Relation Extraction via Reading Comprehension (2017, background): “Bronstein et al. (2015) explore a similar zero-shot setting for event-trigger identification, in which R N +1 is specified by a set of trigger words at test time.”
• Event Detection and Co-reference with Minimal Supervision (2016, methodology): “Motivated by the seed-based event trigger labeling technique employed in Bronstein et al. (2015), we turn to ACE annotation guidelines for event examples described under each event type label.”
• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, background): “…2020; Liu et al., 2020), defini-tions (Chen et al., 2020), structures (Lin et al., 2020; Wang et al., 2019), or a few prototype event triggers (Wang and Cohen, 2009; Dalvi et al., 2012; Pasupat and Liang, 2014; Bronstein et al., 2015; Lai and Nguyen, 2019; Zhang et al., 2021b; Cong et al., 2021).”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, methodology): “, 2018), seed event mentions (Bronstein et al., 2015; Lai and Nguyen, 2019), or question answering (QA) (Du and Cardie, 2020; Liu et al.”