| license: apache-2.0 | |
| # Universal Sentence Encoder | |
| This model is a full precision version of the original [universal-sentence-encoder](https://tfhub.dev/google/universal-sentence-encoder/4), | |
| wrapped by input and output reshaping layers. | |
| These wrapping processing layers change the input signature from Rank-1 (Lists) to Rank-2 (Matrices), | |
| making the model compatible with the serving environments of the Actian Analytics Engine that requires an input dimension of Rank-2 or higher. | |
| ## Description adapted from [TFHub](https://tfhub.dev/google/universal-sentence-encoder/4) | |
| The Universal Sentence Encoder encodes text into high dimensional vectors that can be used for text classification, semantic similarity, | |
| clustering and other natural language tasks. | |
| The model is trained and optimized for greater-than-word length text, such as sentences, phrases or short paragraphs. | |
| It is trained on a variety of data sources and a variety of tasks with the aim of dynamically accommodating a wide variety of natural language understanding tasks. | |
| The input is column of English strings and the output is a column of 512 dimensional vectors. | |
| ## Requirements | |
| - Actian Analytics Engine: 8.0 |