Published: September 10, 2019
Author(s)
Apostol Vassilev (NIST)
Conference
Name: International Conference on Machine Learning, Optimization, and Data Science
Dates: 09/10/2019 - 09/13/2019
Location: Siena, Italy
Citation: LOD 2019: Machine Learning, Optimization, and Data Science, vol. 11943, pp. 360-371
How to model and encode the semantics of human-written text and select the type of neural network to process it are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These properties are closely related to the loss estimates for the trained model. I present a computationally- efficient and accurate feedforward neural network for sentiment prediction capable of maintaining low losses. When coupled with an effective semantics model of the text, it provides highly accurate models with low losses. Experimental results on representative benchmark datasets and comparisons to other methods.
How to model and encode the semantics of human-written text and select the type of neural network to process it are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These properties are closely related to the loss estimates...
See full abstract
How to model and encode the semantics of human-written text and select the type of neural network to process it are not settled issues in sentiment analysis. Accuracy and transferability are critical issues in machine learning in general. These properties are closely related to the loss estimates for the trained model. I present a computationally- efficient and accurate feedforward neural network for sentiment prediction capable of maintaining low losses. When coupled with an effective semantics model of the text, it provides highly accurate models with low losses. Experimental results on representative benchmark datasets and comparisons to other methods.
Hide full abstract
Keywords
deep learning; sentiment analysis; Natural Language Processing
Control Families
None selected
