Discriminative and Generative Transformer-based Models For Situation Entity Classification

2021/09/15 by Mehdi Rezaee, Kasra Darvish, Rezaee, Mehdi +5 · 1 citation
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Quality and Management #FOS: Computer and information sciences #Time Series Analysis and Forecasting #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2109.07434

openalex publication_date 2021/09/15 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to generate the text and learn a SE classifier. Test set and cross-genre evaluations show that when training data is plentiful, the proposed model can improve over the previous discriminative state-of-the-art models. Our approach performs disproportionately better with smaller amounts of training data, but when faced with extremely small sets (4 instances per label), generative RNN methods outperform transformers. Our work provides guidance for future efforts on SE and semantic prediction tasks, and low-label training regimes.

Cited by

• Generative or Discriminative? Revisiting Text Classification in the Era of Transformers

Related

• Building Context-aware Clause Representations for Situation Entity Type Classification
• Rethinking the Two-Stage Framework for Grounded Situation Recognition
• Grounded Situation Recognition with Transformers
• LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
• Recurrent Models for Situation Recognition