Application of English Corpus using Long-Short Term Memory with Multiplicative Attention Algorithm

English corpus is primarily utilized in Natural Language Processing (NLP) by generating an extensive linguistic information for training model. English corpora increase language teaching tools in linguistics by providing insights into grammar, vocabulary, and sematic patterns. However, the English Corpus lies in its huge linguistic diversity and context dependencies that leads to difficulties in accurately determining nuanced meanings. This process affects the performance of NLP specifically managing idiomatic ambiguities, expressions, and evolving language usage. In this research, the Long-Short Term Memory with Multiplicative Attention Algorithm (LSTM-MAA) is proposed for English corpus. In traditional LSTM, the MAA is incorporated to increase the model’s ability to focus on appropriate parts of the input sequence which enhance context representation. The LSTM-MAA enable the model to dynamically adjust its focus that leads to better performance. Mel-Frequency Cepstral Coefficient(MFCC) is used to extract the features while conserving significant phonetic data which enhance the performance of English corpora. The proposedLSTM-MAA achieves a better accuracy of 99.87% compared to the existing methods like Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN).