Hacking Self-attention architectures to address Unsupervised text tasks
Submitted by Venkata Dikshit Pappu (@vdpappu) on Thursday, 11 April 2019
Self-attention architectures like BERT, OpenAI GPT, MT-DNN are current state-of-the art feature extractors for several supervised downstream tasks for text. However, their ability on unsupervised tasks like document/sentence similarity are inconclusive. In this talk, I intend to cover brief overview of self attention architectures for Language Modelling, fine-tuning/feature selection approaches for unsupervised tasks that can be used for a variety of tasks. This talk is for NLP practitioners interested in using Self-attention architectures for their applications.
- Overview of Transformer/Self-attention architectures - BERT
- Document representations using BERT
- Formulating a sentence relevance score with BERT features
- Seaching and ranking feature sub-spaces for specific tasks
- Other reproducible hacks
Venkat is ML Architect working for Ether Labs based out of Bangalore
6+ years of Experience in ML and related fields
Worked on Machine Vision and NLP solutions for Retail, Customer electronics, embedded verticals
Venkat leads ML team at Ether Labs and his team is responsible for building scalable AI components for Ether Video collaboration platform - Vision, NLU and Graph learning.