▌ ▐ ▐▀▌ █ █▀▌ ▐▀▌ ▌ ▐ ▐▌▐▌ ▐▀▀ ▀▌▐▌▐▀ █▀█ █▀█ █ █ █ █▀█ █ █ ▐▐▌█ █▀ ▌▐▌▐ ▌ ▐ ▌ ▐ ▐██ ███ ▌ ▐ █▄█ ▐ █ ▐██ ▄▌▐▌▐▄ (W)elcome (A)dvisees (C)alendar (P)ublications (V)ita/Bio/Contact (F)AQ (T)eaching (D)ata + Code (L)inks (B)log (I)mages + Photos Tal(k)s
You enter a dark forest. Standing in front of you is:

An associate professor named Hal Daumé III. He wields appointments in Computer Science and Language Science at UMD where he studies and blogs about natural language processing (ACL, EMNLP) and machine learning (ICML, NIPS). He is currently director of the CLIP lab, and runs the ML reading group. Percy Liang and he built Braque, a news for researchers site. He maintains the structured prediction framework in VW. He is currently teaching CS 421: Artificial Intelligence and CS 828: Reinforcement Learning in Fall 2016.

Recent Publications:

Guest Editor’s Introduction to the Special Issue on Domain Adaptation for Vision Applications
Dong Xu, Rama Chellappa, Trevor Darrell and Hal Daumé III
IJCV, 2015

Why discourse affects speakers’ choice of referring expressions
Naho Orita, Eliana Vornov, Naomi H Feldman and Hal Daumé III
Conference of the Association for Computational Linguistics (ACL), 2015
[Abstract] [BibTeX]

Learning Reductions that Really Work
Alina Beygelzimer, Hal Daumé III, John Langford and Paul Mineiro
IEEE Proceedings, 2015
[Abstract] [BibTeX]

Learning to search better than your teacher
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III and John Langford
International Conference on Machine Learning (ICML), 2015
[Abstract] [BibTeX]

Syntax-based Rewriting for Simultaneous Machine Translation
He He, Alvin Grissom II, Jordan Boyd Graber and Hal Daumé III
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015
[Abstract] [BibTeX]

More papers please!

Recent Talks:

Locally optimal learning to search and distant supervision
December 2015, UMD CS Research Seminar
[PDF] [ODP] [Video]

Imitation learning and recurrent neural networks mashup
December 2015, CIFAR NCAP Workshop

Algorithms that learn to think of their feet
October 2015, UC Santa Cruz

Interpretese vs Translationese
August 2015, Shonan Workshop

Advances in Structured Prediction
June 2015, ICML Tutorial (with John Lanford)
[PDF Part 1] [ODP Part 1] [PDF Part 2] [Video]

Hands-on Learning to Search for Joint Prediction
May 2015, NAACL Tutorial
[PDF Part 1] [PDF Part 2] [PDF Part 3] [Video]

Algorithms that learn to think on their feet
May 2015, Invited Talk at ICLR
[PDF] [ODP] [Video]

More talks please!

Current Advisees:
 * Hadi Amiri, postdoc working on social media analysis
 * Amittai Axelrod, postdoc (with Philip Resnik) working on machine translation
 * Snigdha Chaturvedi, Ph.D. student working on NLP for online education
 * He He, Ph.D. student (with Jordan Boyd-Graber) working on structured prediction
 * Mohit Iyyer, Ph.D. student (with Jordan Boyd-Graber) working on deep learning for NLP
 * Sudha Rao, Ph.D. student (with Philip Resnik) working on machine translation
Contact information:
    email: me AT hal3 DOT name               skype: haldaume3
    phone: 301-405-1073                    twitter: haldaume3
   office: AVW 3227                         github: hal3
I can't reply to all prospective students email; please read this before emailing me.

credits: design and font inspired by Seth Able's LoRD, some images converted to ANSI using ManyTools, original drawing of me by anonymous.
last updated on twenty two november, two thousand sixteen.