Combining BERT and Multiple Embedding Methods with the Deep Neural Network for Humor Detection

Abstract

Humor detection from written sentences has been an interesting and challenging task in the last few years. Most of the prior studies have been explored the traditional approaches of embedding, e.g., Word2Vec or Glove. Recently Bidirectional Encoder Representations from Transformers (BERT) sentence embedding has also been used for this task. In this paper, we propose a framework for humor detection in short texts taken from news headlines. Our proposed framework 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 humor detection.