See how to do topic modeling using Roberta and transformers. We will use a pre-trained Roberta model finetuned on the NLI dataset for getting embeddings and then do topic modelling.
See how to do conversational response generation using DialoGPT – a SOTA dialogue response generation model for multiturn conversations.
See how ONNX can be used for faster CPU inference performance using the Huggingface transformer NLP pipeline with few changes.
Text2TextGeneration is a single pipeline for all kinds of NLP tasks like Question answering, sentiment classification, question generation, translation, paraphrasing, summarization, etc.
Let’s see how the Text2TextGeneration pipeline by Huggingface transformers can be used for these tasks.
Cluster text documents using BERT embeddings and Kmeans. See how you can apply the K-means algorithm on the embedding to cluster documents.
To get semantic document similarity between documents, get the embedding using BERT and calculate the cosine similarity score between them.
Summarize text document using Huggingface transformers and BERT. Use different transformer models for summary and findout the performance.