Integrating extracted information from bert and multiple embedding methods with the deep neural network for humour detection

TL;DR

This paper introduces IBEN, a novel framework combining multi-layer BERT embeddings, external embeddings, and multi-kernel CNNs for improved humour detection in short texts like news headlines.

Contribution

It proposes a new approach that integrates layered BERT embeddings with external embeddings and multi-kernel CNNs for humour detection, outperforming traditional methods.

Findings

High accuracy in humour detection on news headlines

Effective use of BERT layer weights for feature extraction

Enhanced sentence representation with multi-kernel CNNs

Abstract

Humour detection from sentences has been an interesting and challenging task in the last few years. In attempts to highlight humour detection, most research was conducted using traditional approaches of embedding, e.g., Word2Vec or Glove. Recently BERT sentence embedding has also been used for this task. In this paper, we propose a framework for humour detection in short texts taken from news headlines. Our proposed framework (IBEN) attempts to extract information from written text via the use of different layers of BERT. After several trials, weights were assigned to different layers of the BERT model. The extracted information was then sent to a Bi-GRU neural network as an embedding matrix. We utilized the properties of some external embedding models. A multi-kernel convolution in our neural network was also employed to extract higher-level sentence representations. This framework performed very well on the task of humour detection.