I am the Chief Scientist at Salesforce. Previously, I was the Founder and CEO/CTO of MetaMind which was acquired by Salesforce in 2016. My vision is to improve artificial intelligence and make it easily accessible to everyone. I enjoy research in deep learning, natural language processing and computer vision. This New York Times article talks about some of the work we are doing. I teach CS224d - Deep Learning for Natural Language Processing at Stanford. Here's a 1.5h short version of that course. I got my PhD in the CS Department at Stanford, advised by Chris Manning and Andrew Ng. I'm on Twitter and enjoy photography.

Jan 6, 2017

Start of CS224n - Natural Language Processing with Deep Learning, together with Chris Manning

Nov 10

Talk at San Francisco AI meetup about recent deep learning for NLP models

Oct 6

Einstein Keynote at Dreamforce -- Video

Sep 24

Deep Learning for NLP in 1.5h, Deep Learning Summer School at Stanford. Video

Mar 30

Start of my class CS224d: Deep Learning for Natural Language Processing at Stanford

Publications

List of papers on Google scholar. We did a Deep Learning Tutorial at ACL 2012 and NAACL 2013.

2016

Dynamic Coattention Networks For Question Answering, Caiming Xiong, Victor Zhong, Richard Socher
[ pdf, blog post, Best model on Stanford Question Answering Dataset ]

A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks, Kazuma Hashimoto, Caiming Xiong, Yoshimasa Tsuruoka, Richard Socher
[ pdf, blog post ]

Quasi-Recurrent Neural Networks, James Bradbury, Stephen Merity, Caiming Xiong, Richard Socher
[ pdf, blog post ]

Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling, Hakan Inan, Khashayar Khosravi, Richard Socher
[ pdf ]

A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs, Shayne Longpre, Sabeek Pradhan, Caiming Xiong, Richard Socher
[ pdf ]

Pointer Sentinel Mixture Models, Stephen Merity, Caiming Xiong, James Bradbury, Richard Socher
[ pdf, new dataset ]

MetaMind Neural Machine Translation System for WMT 2016, James Bradbury, Richard Socher
Proceedings of the First Conference on Machine Translation. Association for Computational Linguistics.
[ pdf, 2nd Place in the competition ]

Dynamic Memory Networks for Visual and Textual Question Answering, Caiming Xiong, Stephen Merity, Richard Socher
The 33rd International Conference on Machine Learning (ICML 2016). [ pdf , New York Times, MIT Technology Review ]

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing, Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, Richard Socher
The 33rd International Conference on Machine Learning (ICML 2016).
Previous versions appeared at NIPS 2015 Deep Learning Symposium; NIPS 2015 workshop on Reasoning, Attention and Memory Workshop
[ pdf , Wired, MIT Tech Review, MetaMind announcement ]

2015

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks, Kai Sheng Tai, Richard Socher, and Christopher D. Manning
Association for Computational Linguistics 2015 Conference (ACL 2015). [ pdf , code ]

2014

Recursive Deep Learning for Natural Language Processing and Computer Vision, Richard Socher
PhD Thesis, Computer Science Department, Stanford University
[ pdf, 2014 Arthur L. Samuel Best Computer Science PhD Thesis Award ]

Global Belief Recursive Neural Networks, Romain Paulus, Richard Socher, Christopher D. Manning
Advances in Neural Information Processing Systems (NIPS 2014)
[ pdf ]

Aspect Specific Sentiment Analysis using Hierarchical Deep Learning, Himabindu Lakkaraju, Richard Socher, Chris Manning.
NIPS Workshop on Deep Learning and Representation Learning, 2014
[ pdf ]

Glove: Global Vectors for Word Representation, Jeffrey Pennington, Richard Socher and Christopher D. Manning
Conference on Empirical Methods in Natural Language Processing (EMNLP 2014)
[ pdf , website with word vectors ].

A Neural Network for Factoid Question Answering over Paragraphs, Mohit Iyyer, Jordan Boyd-Graber, Leonardo Claudino, Richard Socher and Hal Daumé III
Conference on Empirical Methods in Natural Language Processing (EMNLP 2014)
[ pdf, website with dataset, code, etc. ].

Grounded Compositional Semantics for Finding and Describing Images with Sentences, Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, Andrew Y. Ng.
Transactions of the Association for Computational Linguistics (TACL 2014), Presented at ACL 2014.
[ pdf ].

Scaling Short-answer Grading by Combining Peer Assessment with Algorithmic Scoring, Chinmay Kulkarni, Richard Socher, Michael S. Bernstein, Scott R. Klemmer.
2014 ACM Conference on Learning at Scale [ pdf ].

2013

Demonstration: etcml.com - easy text classification with machine learning, Richard Socher, Romain Paulus, Bryan McCann, Kai Sheng Tai, JiaJi Hu, Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS 2013). [ Website to easily train and share text classifiers; Press: GigaOM, Stanford ]

Reasoning With Neural Tensor Networks for Knowledge Base Completion, Richard Socher*, Danqi Chen*, Christopher D. Manning, Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS 2013). [ pdf, website ]

Zero-Shot Learning Through Cross-Modal Transfer, Richard Socher, Milind Ganjoo, Christopher D. Manning, Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS 2013). [ pdf, website ]

Grounded Compositional Semantics for Finding and Describing Images with Sentences, Richard Socher, Quoc V. Le, Christopher D. Manning, Andrew Y. Ng.
Deep Learning Workshop at NIPS 2013 (see TACL 2014 version)

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank, Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Chris Manning, Andrew Ng and Chris Potts.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2013, Oral). [ pdf, Supplementary Material, Website with Live Demo and Downloads; Press: Stanford release, Wired, Boston Globe Related Kaggle Competition ];

Bilingual Word Embeddings for Phrase-Based Machine Translation, Will Zou, Richard Socher, Daniel Cer and Christopher Manning.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2013, Short). [ pdf ]

Parsing with Compositional Vector Grammars, Richard Socher, John Bauer, Christopher D. Manning and Andrew Y. Ng.
Association for Computational Linguistics 2013 Conference (ACL 2013). [ pdf , website ]

Better Word Representations with Recursive Neural Networks for Morphology, Thang Luong, Richard Socher, Christopher D. Manning.
Conference on Computational Natural Language Learning (CoNLL 2013). [ pdf, website with vectors ]

Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors, Danqi Chen, Richard Socher, Christopher D. Manning, Andrew Y. Ng.
International Conference on Learning Representations (ICLR 2013, Workshop Track). [ pdf, website ]

Zero-Shot Learning Through Cross-Modal Transfer, Richard Socher, Milind Ganjoo, Hamsa Sridhar, Osbert Bastani, Christopher D. Manning, Andrew Y. Ng.
International Conference on Learning Representations (ICLR 2013, Workshop Track, Oral). [ pdf, website ]

2012

Convolutional-Recursive Deep Learning for 3D Object Classification, Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning and Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS 2012). [ pdf, website ]

Semantic Compositionality through Recursive Matrix-Vector Spaces, Richard Socher, Brody Huval, Christopher D. Manning and Andrew Y. Ng.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2012, Oral). [ pdf, website ]

Improving Word Representations via Global Context and Multiple Word Prototypes, Eric H. Huang, Richard Socher, Christopher D. Manning and Andrew Y. Ng.
Association for Computational Linguistics 2012 Conference (ACL 2012). [ pdf, website ]

Stanford’s System for Parsing the English Web, David McClosky, Wanxiang Che, Marta Recasens, Mengqiu Wang, Richard Socher, and Christopher D. Manning
In Proceedings of First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL at NAACL, 2012). [ pdf, bib ]

2011

Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection, Richard Socher, Eric H. Huang, Jeffrey Pennington, Andrew Y. Ng, and Christopher D. Manning.
Advances in Neural Information Processing Systems (NIPS 2011). [ pdf, website ]

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions, Richard Socher, Jeffrey Pennington, Eric Huang, Andrew Y. Ng, and Christopher D. Manning.
Conference on Empirical Methods in Natural Language Processing (EMNLP 2011, Oral). [ pdf, website ]

Parsing Natural Scenes and Natural Language with Recursive Neural Networks, Richard Socher, Cliff Lin, Andrew Y. Ng, and Christopher D. Manning.
The 28th International Conference on Machine Learning (ICML 2011). Distinguished Application Paper Award. [ pdf, video, website ]

Spectral Chinese Restaurant Processes: Nonparametric Clustering Based on Similarities, Richard Socher, Andrew Maas, Christopher D. Manning.
Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011). [ pdf ]

2010

Connecting Modalities: Semi-supervised Segmentation and Annotation of Images Using Unaligned Text Corpora, Richard Socher and Li Fei-Fei.
IEEE Computer Vision and Pattern Recognition (CVPR 2010). [ pdf ]

2009

A Bayesian analysis of dynamics in free recall, Richard Socher, Sam J. Gershman, Adler Perotte, Per Sederberg, Ken A. Norman, and David M. Blei.
Advances in Neural Information Processing Systems 22 (NIPS 2009). [ pdf ]

Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework, Li-Jia Li, Richard Socher, and Li Fei-Fei.
IEEE Computer Vision and Pattern Recognition (CVPR 2009, Oral). [ pdf ]

ImageNet: A Large-Scale Hierarchical Image Database, Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei.
IEEE Computer Vision and Pattern Recognition (CVPR 2009). [ pdf ]

Before

A Learning Based Hierarchical Model for Vessel Segmentation, Richard Socher, Adrian Barbu, and Dorin Comaniciu.
In 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2008, Oral). [ pdf ]

Combining Contexts in Lexicon Learning for Semantic Parsing, Richard Socher, Chris Biemann, and Rainer Osswald.
Proceedings of NODALIDA 2007, Tartu, Estonia. [ pdf ]

Theses

PhD Thesis: Recursive Deep Learning for Natural Language Processing and Computer Vision, Computer Science Department, Stanford University

Masters Thesis: A Learning-Based Hierarchical Model for Vessel Segmentation, Saarland University, 2008, grade 1.0 A+

Bachelor Thesis: Automatic Extension of Semantic Lexicons with a Bootstrapping Algorithm, Leipzig University, 2006, grade 1.0 A+