Feature-Enriched Character-Level Convolutions for Text Regression

Paetzold, Gustavo Henrique; Specia, Lucia

doi:10.18653/v1/w17-4765

Cited by 3 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dereli and Saraclar (2019) proposed a convolutional neural network model and applied transfer learning to forecast stock return volatility from annual reports. Paetzold and Specia (2017) proposed and tested the text regression model using deep convolutional neural networks and multi-layer perceptron on two text regression tasks. Furthermore, Ye et al (2021) developed a text regression-based model with hierarchical structure and multi-head attention mechanism for specific news domain push.…”

Section: Text Regressionmentioning

confidence: 99%

Interpretable deep learning based text regression for financial prediction

Liang

Zhang

2023

Expert Systems

View full text Add to dashboard Cite

Text regression is an important task in natural language processing (NLP), which aims to predict continuous numerical values associated with text. Previous work focused on linear text regression requiring manual feature selection for financial prediction. Recently, non-linear text regression through neural network models has become a trend. However, most models rely only on convolutional neural networks (CNN) and suffer from insufficient interpretability. In this paper, we propose a deep neural network model named EM-CBA for text regression and further interpret the model. The proposed model is powered by word EMbedding, CNN, Bidirectional long short-term memory (Bi-LSTM) and Attention mechanism. The proposed EM-CBA takes financial report texts as input and predicts a financial metric named return on assets (ROA). We conduct comprehensive experiments on a dataset about the reports of enterprises. Experimental results show that the proposed model provides more accurate predictions of enterprises' metrics than previous convolutional neural network models and other classical models. The validity of each module of the model is also verified. Finally, we demonstrate a way of performing analysis in words change and results errors to intuitively interpret the effect of different text inputs on the model. The analysis demonstrates that the model is able to use information about sentiment words to analyse their associated contexts to revise the predictions.

show abstract

Section: Text Regressionmentioning

confidence: 99%