Intelligent Recognition English Translation Model Based on Embedded Machine Learning and Improved GLR Algorithm

Most of the popular translation models are based on encoder-decoder architecture and belong to autoregressive model. When decode, they generate current sequence according generated before. This process is not parallel. The generalized maximum likelihood ratio detection (GLR) algorithm model cannot effectively guarantee overlapping accurate results English detection. To improve recognition rate phrases meanings, this paper proposes an intelligent for embedded machine learning improved GLR algorithm. A corpus 520000 used training. And we compare analyze different corpora with other traditional algorithms. Words analytic linear structure. syntactic function table corrects ambiguity between Chinese structures in some speech finally retains content. research shows that accuracy more than 96.58%, which 23% higher classical semantic recognition. Statistical dynamic storage make it suitable provide a new method translation.