Describes Chris Tanner’s research interests in Machine Learning, Deep Learning, and Natural Language Processing (NLP). Brown University, Spotify, IBM Research, Johns Hopkins HLT COE, MIT Lincoln Laboratory, MITLL, Department of Defense, Google, Florida Tech, UCLA.



I am a lecturer at Harvard, within the School of Engineering and Applied Sciences, working directly with the Institute for Applied Computational Science (IACS). I teach:

My interests are in machine learning / deep learning, particularly natural language processing (NLP). My PhD dissertation focused on cross-document co-reference resolution for both entities and events. I was fortunate to be Dr. Eugene Charniak’s final PhD student.

In general, I’m most passionate about discourse, semantics, and understanding, but I tend to get excited about a multitude of Machine Learning problems.


During my career within academia, industry, and the government, my work has concerned:

  • coreference resolution

  • link prediction

  • face recognition

  • named-entity disambiguation

  • topic modelling

  • machine translation

  • streaming algorithms for NLP

  • anomaly detection

  • adaptive web personalization

  • speech recognition via active learning

  • error-correcting codes

  • social network analysis

  • 2d pattern recognition

  • animats-based learning (swarm intelligence)


You can download my resume here.


Chris Tanner and Eugene Charniak. Symbiotic Coreference Resolution for Entities and Events. (In Submission).

Chris Tanner and Eugene Charniak. Toward Featureless Event Coreference Resolution via Conjoined Convolutional Neural Networks. (In Submission).

Chris Tanner and Eugene Charniak. A Hybrid Generative/Discriminative Approach to Citation Prediction. NAACL, 2015

Chris Tanner, Stephen Chen, Byron Wallace, and Eugene Charniak. Discriminative Approaches to Citation Evidence Linking and Discourse Prediction. TAC Workshop (NIST), 2014


Unpublished Papers

The following includes my Master's Thesis and write-ups for course projects long ago:

Chris Tanner. An Exploration of Animats-Based Evolution and Communication. May 2009. UCLA Master's Thesis.

Chris Tanner and Eric Wood. Meerkat Manor: An Approach to Simulated, Genetic Co-Evolution.December 2008.

Chris Tanner and Leslie Choong. Automated Story Conversion: Generating Children Stories from Adult Stories. June 2008. (3-week course project)

Chris Tanner and Leslie Choong. Utilizing Natural Language Processing Conceptual Dependencies to Infer Meaning of 'Dashed Hopes.' May 2008. (3-week course project)

Chris Tanner, Irina Litvin, Amruta Joshi. Social Networks: Finding Highly Similar Users and their Inherit Patterns. February 2008.

Chris Tanner, Chu-Cheng Hsieh, and Keenahn Jung. Understanding Pure Social Networks: Structure, Connectivity, and Patterns of Interests. November 2007.

Chris Tanner. Improving Web Personalization via User Interest Hierarchy and Scoring Techniques. December 2006.

Chris Tanner. Accelerating Artificial Neural Network Learning via Weight Predictions. April 2005.



Some interesting courses I've taken as a student include:

  • Special Topics in Computational Linguistics (Brown)

  • Computational Molecular Biology (Brown)

  • Human-Computer Interaction Seminar (Brown)

  • Computational Linguistics (Brown)

  • The Photo Book (Rhode Island School of Design)

  • Reasoning with Partial Beliefs (UCLA)

  • Approximation Algorithms (UCLA)

  • Statistical Learning (UCLA)

  • Language and Thought (UCLA)

  • Animats-Based Learning (UCLA)

  • Parallel Programming (UCLA)

  • Web Information Management/Data Mining (UCLA)

  • Machine Learning (Florida Tech)

  • Artificial Intelligence (Florida Tech)

  • Neural Networks (Florida Tech)

  • Chaos Math (Florida Tech)

  • Abstract Algebra (Florida Tech)

  • Introductory Analysis (Florida Tech)

  • Numerical Analysis (Florida Tech)