An Artificial Intelligence-based language modeling framework

Abstract

The text entry interaction between human and computer could be noisy. The typing stream is a reflection of users’ typing behavior that includes ones’ fluency of vocabulary, typing habits and typing performance. This research develops an original intermediate layer language modeling framework called Adaptive Language Modeling Intermediate Layer (ALMIL), which can be seen as a communication language layer between human and computer to analyze noisy language stream data and provide users with Text Prediction and Text Correction functions. Then, the ALMIL framework is applied to QWERTY keyboard producing an Intelligent Keyboard hybrid framework, which can be used to analyze users’ typing stream, and accordingly correct typing mistakes and predict users typing intention. An extendable Focused Time-Delay Neural Network (FTDNN) n-gram prediction algorithm is also developed to learn from the users’ typing history and produce text entry prediction and correction based on historical typing stream. Overall, this research pioneers a comprehensive neural network language modeling process based on cross-experiments between extendible inputs, hidden neurons and noise rates, while statistics based traditional methods have failed to consider possible noises of a language stream. The Computer Simulation Results demonstrate that the proposed Intelligent Keyboard performs better than the conventional keyboard in Text Prediction and Text Correction. In practice, a higher prediction rate could be achieved by combining the First Three Hitting Rate with an English word dictionary.