Has Natural Language Processing Contributed to the Success of Deep Learning?

Abstract: Many researchers might reasonably believe that the answer to the  question posed by the title is no, and that machine learning and other areas such as computer vision are primarily responsible for the success of deep learning.  However, contributions from NLP have been critical to the success of deep learning.  Many ideas from the history of NLP in probabilistic language modeling, lexical and distributional semantics, word embeddings, machine translation and linguistic neural models such as RNNs, LSTMs and transformers have contributed substantially to the recent progress in AI. This talk will review these contributions and speculate on how ideas from NLP may continue to contribute to future progress.

About the speaker: Raymond J. Mooney is a Professor in the Department of Computer Science at the University of Texas at Austin where he is also Director of the AI Lab. He received his Ph.D. in 1988 from the University of Illinois at Urbana/Champaign. He is an author of over 200 published research papers, primarily in the areas of machine learning and natural language processing. He was the President of the International Machine Learning Society from 2008-2011, program co-chair for AAAI 2006, general chair for HLT-EMNLP 2005, and co-chair for ICML 1990. He is a Fellow of AAAI, ACM, and ACL and the recipient of the Classic Paper award from AAAI-19 and best paper awards from AAAI-96, KDD-04, ICML-05 and ACL-07.

Visit FAI for Zoom link