A Custom State LSTM Cell for Text Classification Tasks
Επιτομή
Text classification is the task of assigning a class to a document. Machine Learning enables the automation of Text Classification Tasks, amongst others. Recent advances in the Machine Learning field, such as the introduction of Recurrent Neural Networks, Long Short Term Memory and Gated Recurrent Units, have greatly improved classification results. These type of networks include internal memory states that demonstrate dynamic temporal behaviour. In the LSTM cell, this temporal behaviour is supported by two distinct states: current and hidden. We introduce a modification layer within the LSTM cell, where we are able to perform extra state alterations for one or both states. We experiment with 17 single state alterations, 12 for the current state and 5 for the hidden state. We evaluate these alterations in seven datasets that deal with hate speech detection, document classification, human to robot interaction and sentiment analysis. Our results demonstrate an average F1 improvement of 0.5% for the top performing current state alteration and 0.3% for the top performing hidden state alteration. © 2022, Springer Nature Switzerland AG.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Fuzzy Cognitive Maps for Interpretable Image-based Classification
Sovatzidi G., Vasilakakis M.D., Iakovidis D.K. (2022)Image classification is a fundamental component of intelligent vision systems. Developing classifiers capable of explaining how or why a classification result occurs, in a way compatible with human perception, remains a ... -
A comparable study employing weka clustering/classification algorithms for web page classification
Charalampopoulos, I.; Anagnostopoulos, I. (2011)Documents and web pages share many similarities. Thus classification methods used in documents can be applied to advanced web content, with or even without modifications. Algorithms for document and web classification are ... -
A Self-Pruning Classification Model for News
Akritidis L., Fevgas A., Bozanis P., Alamaniotis M. (2019)News aggregators are on-line services that collect articles from numerous reputable media and news providers and reorganize them in a convenient manner with the aim of assisting their users to access the information they ...