SeMemNN: A Semantic Matrix-Based Memory Neural Network for Text Classification

Abstract

Text categorization is the task of assigning labels to documents written in a natural language, and it has numerous real-world applications including sentiment analysis as well as traditional topic assignment tasks. In this paper, we propose 5 different configurations for the semantic matrix-based memory neural network with end-to-end learning manner and evaluate our proposed method on two corpora of news articles (AG news, Sogou news). The best performance of our proposed method outperforms the baseline VDCNN models on the text classification task and gives a faster speed for learning semantics. Moreover, we also evaluate our model on small scale datasets. The results show that our proposed method can still achieve better results in comparison to VDCNN on the small scale dataset. This paper is

Multi-Modality Emotion Recognition Model with GAT-Based Multi-Head Inter-Modality Attention

“…Text : For the text emotion classification, we employed SeMemNN [ 55 ] and trained it from scratch. Fu et al [ 55 ] confirmed that SeMemNN has a good ability to learn semantics and fast training speed on a small sample dataset.…”

“…Text : For the text emotion classification, we employed SeMemNN [ 55 ] and trained it from scratch. Fu et al [ 55 ] confirmed that SeMemNN has a good ability to learn semantics and fast training speed on a small sample dataset. In SeMemNN, two inputs work together to construct the addressing and semantic matrixes, which yield an address vector to read some corresponding information from the semantic matrix.…”

JPS-daprinfo: A Dataset for Japanese Dialog Act Analysis and People-related Information Detection

“…We simply run a text classification based on SeMemNN [6] and BERT [7]. The training-set and testing-set were split as predefined.…”