Skip to content

Document Level Sentiment Analysis v1.0.0

Latest
Compare
Choose a tag to compare
@LifengWang LifengWang released this 05 Dec 07:06
· 1 commit to main since this release

Document Level Sentiment Analysis is an End-to-End deep learning workflow using Hugging Face transformers API to do a "classification" task at document level, to analyze the sentiment of input document containing English sentences or paragraphs.

The workflow showcases how to leverage Intel® Advanced Vector Extensions 512 (Intel® AVX-512) and Intel® Advanced Matrix Extensions (Intel® AMX) to accelerate the performance of Fine Tuning (transfer learning) & Inference of Bert based models such as Bert-Large, Distilbert using movie review datasets such as IMDB and SST2 for the Sentiment Analysis task running on Intel platforms.