Sememe knowledge and auxiliary information enhanced approach for sarcasm detection

Proceedings Paper Computer Science, Artificial Intelligence

Adversarial and Auxiliary Features-Aware BERT for Sarcasm Detection

Avinash Kumar et al.

Summary: The study presents a novel model AAFAB, which combines contextual word embeddings and manually extracted auxiliary features for sarcasm detection, and adversarial training helps generalize parameters better, improving performance compared to various traditional and deep learning models.

CODS-COMAD 2021: PROCEEDINGS OF THE 3RD ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE & MANAGEMENT OF DATA (8TH ACM IKDD CODS & 26TH COMAD) (2021)

Add to Collection

Article Computer Science, Information Systems

A Term Weighted Neural Language Model and Stacked Bidirectional LSTM Based Framework for Sarcasm Identification

Aytug Onan et al.

Summary: This research aims to present an effective sarcasm identification framework on social media data by utilizing neural language models and deep neural networks. The model includes a three-layer stacked bidirectional long short-term memory architecture and introduces an inverse gravity moment based term weighted word embedding model to preserve word-ordering information. The presented model achieves promising results with a classification accuracy of 95.30% for the sarcasm identification task.

IEEE ACCESS (2021)

Add to Collection

Article Computer Science, Information Systems