Semi-supervised New Event Type Induction and Event Detection

By Lifu Huang, Heng Ji. 2020

64 citations recorded by the source corpus.

Most previous event extraction studies assume a set of target event types and corresponding event annotations are given, which could be very expensive. In this paper, we work on a new task of semi-supervised event type induction, aiming to automatically discover a set of unseen types from a given corpus by leveraging annotations available for a few seen types. We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations. A variational autoencoder is further introduced to enforce the reconstruction of each event mention conditioned on its latent type distribution. Experiments show that our approach can not only achieve state-of-the-art performance on supervised event detection but also discover high-quality new event types.

Subfields: Artificial Intelligence, Information Systems

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. Lifu Huang
2. Shuaicheng Zhang
3. Lifu Huang
4. Sijia Wang
5. Mo Yu
6. Qiang Ning
7. Nanyun Peng
8. Dan Roth

In Information Systems

1. Shuaicheng Zhang
2. Lifu Huang
3. Sijia Wang
4. Lifu Huang
5. Mo Yu
6. Qiang Ning

Citations in the corpus

• Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer (2021, background): “Progress in natu-ral language processing, especially information extraction (Lin et al., 2020; Huang and Ji, 2020), has helped automate the identification of each single S1: Israel's prime minister has ( e 1 : apologised ) to Turkey for " any errors that could have led to loss of life " during the…”
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2021, unknown): “, 2019) and latent representations (Huang and Ji, 2020).”
• The Art of Prompting: Event Detection based on Type Specific Prompts (2022, background): “However, they cannot be effectively generalized to new languages, domains or types, especially when the annotations are not enough (Huang et al., 2016; Huang and Ji, 2020; Lai et al., 2020b; Shen et al., 2021) or there is no annotation available (Lyu et al.”