Deep Learning Techniques for Named Entity Recognition: An Enterprise Perspective
Model developers traditionally use regression models like Multi-class logistic regression and Conditional Random Fields (CRF) to achieve good accuracies in Named Entity Recognition (NER) tasks. However, such models perform sub-optimally with noisy datasets, like voice-enabled applications. We present a deep learning model that uses Long Short-term Memory (LSTM) cells and feature engineering to outperform most state-of-the-art models, enabling our systems to power applications were noisy input is expected.
Vijay Ramakrishnan is a machine learning researcher at Cisco. He is a core member of the Mindmeld team within Cisco, developing Artificial Intelligence (AI) and Natural Language Processing (NLP) applications for Cisco’s flagship products. He is an expert practitioner in developing NLP models and a leading figure in building deep domain conversational AI products. He has built voice and chat assistants for fortune 500 companies at Mindmeld Inc. before it was acquired by Cisco in July 2017. His work combines basic research and software to build state-of-the art AI models for conversational products.