4 - 5 OCTOBER 2017 / EXCEL LONDON

Vijay Ramakrishnan

Company: Cisco

Job Title: Deep Learning Researcher

Vijay Ramakrishnan

Vijay Ramakrishnan is a deep learning researcher at Cisco, working on chat and voice assistants in our products. He previously worked at Mindmeld Inc, which was acquired by Cisco in June 2017.

LinkedIn

Vijay Ramakrishnan Seminars

  • Using deep learning and domain specific enterprise data to build state-of-the-art Entity Recognition models for your voice and chat AI products Wed 4th Oct 11:00 - 11:30

    Using deep learning and domain specific enterprise data to build state-of-the-art Entity Recognition models for your voice and chat AI products

    Currently, Named Entity Recognition (NER) tasks use shallow machine learning models like Maximum Entropy Markov Models or Multi-class logistic regression to get good accuracies on Natural Language Processing tasks. More recently, deep neural models, especially recurrent neural networks like Long short-term memory (LSTM) have given state-of-the-art accuracies on NER data. We present a hybrid model that uses gazetteer data with a bi-directional LSTM model to beat current state-of-the-art accuracies, enabling our systems to power IOT type applications which have a high transcription error rate.

    Speaker

    Vijay Ramakrishnan

    Vijay RamakrishnanMore

    Time / Place

    Wed 4th Oct 11:00 to 11:30

    AI in the Enterprise

Top