Learning Prototype Representations Across Few-Shot Tasks for Event Detection

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5270–5277 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 5270 Learning Prototype Representations Across Few-Shot Tasks for Event Detection Viet Dac Lai1, Franck Dernoncourt2, Thien Huu Nguyen1,3 1 Dept. of Computer and Information Science, University of Oregon, Eugene, OR, USA 2 Adobe Research, San Jose, CA, USA 3 VinAI Research, Vietnam {vietl,thien}@cs.uoregon.edu dernonco@adobe.com Abstract We address the sampling bias and outlier is- sues in few-shot learning for event detection, a subtask of information extraction. We pro- pose to model the relations between training tasks in episodic few-shot learning by intro- ducing cross-task prototypes. We further pro- pose to enforce prediction consistency among classifiers across tasks to make the model more robust to outliers. Our extensive experiment shows a consistent improvement on three few- shot learning datasets. The findings suggest that our model is more robust when labeled data of novel event types is limited. The source code is available at http://github.com/ laiviet/fsl-proact. 1 Introduction In Information Extraction, Event Detection (ED) is an important task that aims to identify and classify event triggers of predefined event types in text (Walker et al., 2006). Event triggers are words/phrases that most clearly indicate the occur- rence of events. For example, an event detector should recognize the word homicide in the fol- lowing sentence as a trigger word of event type life.die.death-caused-by-violent-events: ... the medical examiner believed the manner of death was an accident rather than a homicide. Typical ED systems follow a supervised learning scheme that requires a large amount of labeled data for each predefined event type (Ji and Grishman, 2008; Nguyen and Grishman, 2015; Chen et al., 2015; Nguyen et al., 2021). Unfortunately, this requirement is usually too costly to achieve in real applications where novel event types emerge and only a few examples are available (Huang et al., 2018). As such, an ED model should be prepared to extract triggers of novel event types (i.e., beyond those provided in the training data) for which only a few examples are provided. This learning schema is known as Few-Shot Learning (FSL) for ED. To emulate the learning from few examples in ED, N-way K-shot episodic training is often used to exploit existing datasets (Lai et al., 2020b; Deng et al., 2020; Lai et al., 2020a, 2021). In each train- ing iteration, a small subset (i.e. support set) of N event types with K examples per type is sampled from the training data. Unfortunately, the sample size is so small (K ∈ [1, 10]) that the FSL models might suffer from sample bias, thus hindering the generalization to novel event types. Prototypical network is a popular metric-based few-shot learning model (Snell et al., 2017) that has been explored for FSL ED (Lai et al., 2020b; Deng et al., 2020). It introduces a prototype vector for each event type by averaging the representations of the instances of that type. A non-parametric classi- fier then predicts the event type of a query …

Content truncated to 500 words