mohit iyyer

miyyer@cs.umass.edu // CV // Scholar // github // twitter

I am an assistant professor in computer science at UMass Amherst. Previously, I was a Young Investigator at AI2; before that, I completed my PhD at the University of Maryland, College Park, advised by Jordan Boyd-Graber and Hal Daumé III. My research interests lie broadly in natural language processing and machine learning. Much of my work uses deep learning to model language at the discourse level. Problems in this vein that I'm currently excited about include:

(1) generating long, coherent units of text
(2) answering questions about documents
(3) understanding narratives in fictional text

Feb. 2018: two papers to appear at NAACL 2019 (unsupervised parsing, computational literary criticism)
Nov. 2018: talk at the University of Antwerp
Nov. 2018: talk at WPI CS Colloquium
Oct. 2018: talk at UVM Symposium on the Science of Stories
Aug. 2018: three papers to appear at EMNLP 2018 (QuAC, (un)interpretability, and sentiment reproducibility)
Jul. 2018: talk at TTIC Language Generation workshop
Jun. 2018: ELMo won best long paper at NAACL 2018!
Mar. 2018: talk at USC/ISI NL Seminar
Feb. 2018: three papers to appear at NAACL 2018 (adversarial paraphrasing, ELMo, and image colorization)
Feb. 2018: talk at Ursinus College on applications of machine learning to the digital humanities
Jan. 2018: talk at Indian Institute of Science, Bengaluru
Oct. 2017: submit your QA system to our human-computer QA competition at NIPS 2017!
Apr. 2017: COMICS data and code released here!
Jan. 2017: talk at CU Boulder Stats, Optimization, and Machine Learning seminar
Nov. 2016: talk at UMass Machine Learning & Friends Lunch
Nov. 2016: new paper on understanding comic book narratives and characters.
Nov. 2016: new paper and associated dataset for sequential semantic parsing.
Jun. 2016: our paper on characterizing fictional relationships won best long paper at NAACL 2016!
Apr. 2016: we are organizing a workshop at NAACL 2016 on human-computer question answering with great invited speakers and accepted papers!
May 2015: our quiz bowl robot recently faced off against a team of four Jeopardy champions. Watch the introduction to learn how it works and then check out the actual match! If you're interested, code for the entire system is also available.

STUDENTS Nader Akoury, Kalpesh Krishna, Tu Vu // Interested in working with me? Click here for more info.

TEACHING Spring 2019: Deep Learning for Natural Language Processing (CS 690D)
Fall 2018: Introduction to Natural Language Processing (CS 585)

publications

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders.
Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer, Andrew McCallum.
NAACL 2019

bibtex

@inproceedings{DIORA2019,
Author = {Andrew Drozdov and Patrick Verga and Mohit Yadav and Mohit Iyyer and Andrew McCallum},
Booktitle = {North American Association for Computational Linguistics},
Year = "2019",
Title = {Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders}
}

Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism
Shufan Wang, Mohit Iyyer
NAACL 2019 (short)

bibtex

@inproceedings{Wang2019,
Author = {Shufan Wang and Mohit Iyyer},
Booktitle = {North American Association for Computational Linguistics},
Year = "2019",
Title = {Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism}
}

QuAC: Question Answering in Context.
Eunsol Choi*, He He*, Mohit Iyyer*, Mark Yatskar*, Wen-tau Yih, Yejin Choi, Percy Liang, Luke Zettlemoyer.
EMNLP 2018

project page // datasheet // bibtex

@inproceedings{ChoiQuAC2018,
Author = {Eunsol Choi and He He and Mohit Iyyer and Mark Yatskar and Wen-tau Yih and Yejin Choi and Percy Liang and Luke Zettlemoyer},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = "2018",
Title = {QuAC: Question Answering in Context}
}

Pathologies of Neural Models Make Interpretation Difficult.
Shi Feng, Eric Wallace, Alvin Grissom II, Mohit Iyyer, Pedro Rodriguez and Jordan Boyd-Graber
EMNLP 2018

bibtex

@inproceedings{FengRAWR2018,
Author = {Shi Feng and Eric Wallace and Alvin Grissom II and Mohit Iyyer and Pedro Rodriguez and Jordan Boyd-Graber},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = "2018",
Title = {Pathologies of Neural Models Make Interpretation Difficult}
}

Revisiting the Importance of Encoding Logic Rules in Sentiment Classification.
Kalpesh Krishna, Preethi Jyothi, Mohit Iyyer
EMNLP 2018 (short)

code + data // bibtex

@inproceedings{KrishnaRevisit2018,
Author = {Kalpesh Krishna and Preethi Jyothi and Mohit Iyyer},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = "2018",
Title = {Revisiting the Importance of Encoding Logic Rules in Sentiment Classification}

Adversarial Example Generation with Syntactically Controlled Paraphrase Networks.
Mohit Iyyer*, John Wieting*, Kevin Gimpel, Luke Zettlemoyer.
NAACL 2018

code + data // video // bibtex

@inproceedings{IyyerSCPN2018,
Author = {Mohit Iyyer and John Wieting and Kevin Gimpel and Luke Zettlemoyer},
Booktitle = {North American Association for Computational Linguistics},
Year = "2018",
Title = {Adversarial Example Generation with Syntactically Controlled Paraphrase Networks}
}

Deep Contextualized Word Representations.
Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer.
NAACL 2018 (best long paper)

code // video // bibtex

@inproceedings{PetersELMo2018,
Author = {Matthew E. Peters and Mark Neumann and Mohit Iyyer and Matt Gardner and Christopher Clark and Kenton Lee and Luke Zettlemoyer},
Booktitle = {North American Association for Computational Linguistics},
Year = "2018",
Title = {Deep contextualized word representations}
}

Learning to Color from Language.
Varun Manjunatha*, Mohit Iyyer*, Jordan Boyd-Graber, Larry Davis.
NAACL 2018 (short)

code // bibtex

@inproceedings{Manjunatha2018,
Author = {Varun Manjunatha and Mohit Iyyer and Jordan Boyd-Graber and Larry Davis},
Booktitle = {North American Association for Computational Linguistics},
Year = "2018",
Title = {Learning to Color from Language}
}

Search-based Neural Structured Learning for Sequential Question Answering.
Mohit Iyyer, Wen-tau Yih, and Ming-Wei Chang.
ACL 2017

code // data // bibtex // previous version

@inproceedings{IyyerSQA2016,
Author = {Mohit Iyyer and Wen-tau Yih and Ming-Wei Chang},
Booktitle = {Association for Computational Linguistics},
Year = "2017",
Title = {Search-based Neural Structured Learning for Sequential Question Answering}
}

The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives.
Mohit Iyyer*, Varun Manjunatha*, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daumé III, and Larry Davis.
CVPR 2017 (spotlight)

code + data // video // bibtex // press: mit tech review, digital trends

@inproceedings{IyyerComics2016,
Author = {Mohit Iyyer and Varun Manjunatha and Anupam Guha and Yogarshi Vyas and Jordan Boyd-Graber 
and Hal {Daum\'{e} III} and Larry Davis},
Booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
Year = "2017",
Title = {The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives}
}

Unsupervised Learning of Evolving Relationships Between Literary Characters.
Snigdha Chaturvedi, Mohit Iyyer, and Hal Daumé III.
AAAI 2017

bibtex

@inproceedings{Chaturvedi:Iyyer:Daume-III-2016,
Author = {Snigdha Chaturvedi and Mohit Iyyer and Hal {Daum\'{e} III}},
Booktitle = {Association for the Advancement of Artificial Intelligence},
Year = {2017},
Title = {Unsupervised Learning of Evolving Relationships Between Literary Characters},
}

Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships.
Mohit Iyyer, Anupam Guha, Snigdha Chaturvedi, Jordan Boyd-Graber, and Hal Daumé III.
NAACL 2016 (best long paper)

code + data // supplementary // slides // video // bibtex // press: aeon

@inproceedings{Iyyer:Guha:Chaturvedi:Boyd-Graber:Daume-III-2016,
Author = {Mohit Iyyer and Anupam Guha and Snigdha Chaturvedi and Jordan Boyd-Graber and Hal {Daum\'{e} III}},
Booktitle = {North American Association for Computational Linguistics},
Location = {San Diego, CA},
Year = {2016},
Title = {Feuding Families and Former Friends: Unsupervised Learning for Dynamic Fictional Relationships},
}

"A Distorted Skull Lies in the Bottom Center..." Identifying Paintings from Text Descriptions.
Anupam Guha, Mohit Iyyer, and Jordan Boyd-Graber.
NAACL Human-Computer QA Workshop, 2016

data // bibtex

@inproceedings{Guha:Iyyer:Boyd-Graber-2016,
Author = {Anupam Guha and Mohit Iyyer and Jordan Boyd-Graber},
Booktitle = {NAACL Human-Computer Question Answering Workshop},
Location = {San Diego},
Year = {2016},
Title = {A Distorted Skull Lies in the Bottom Center: Identifying Paintings from Text Descriptions},
}

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, and Richard Socher.
ICML 2016

bibtex

@inproceedings{DMN2016,
Author = {Ankit Kumar and Ozan Irsoy and Peter Ondruska and Mohit Iyyer and James Bradbury and 
Ishaan Gulrajani and Victor Zhong and Romain Paulus and Richard Socher}, 
Booktitle = {International Conference on Machine Learning},
Year = {2016}, 
Title = {Ask Me Anything: Dynamic Memory Networks for Natural Language Processing},
}

Interactive Incremental Question Answering.
Jordan Boyd-Graber, Mohit Iyyer, He He, and Hal Daumé III.
NIPS Demonstration Track, 2015 (outstanding demonstration)

bibtex

@inproceedings{Boyd-Graber:Iyyer:He:Daume-III-2015,
Author = {Jordan Boyd-Graber and Mohit Iyyer and He He and Hal {Daum\'{e} III}},
Booktitle = {Neural Information Processing Systems},
Location = {Montreal, Canada},
Year = {2015},
Title = {Interactive Incremental Question Answering},
}

Deep Unordered Composition Rivals Syntactic Methods for Text Classification.
Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, and Hal Daumé III.
ACL 2015

code + data // slides // video // bibtex

@inproceedings{Iyyer:Manjunatha:Boyd-Graber:III}-2015,
Title = {Deep Unordered Composition Rivals Syntactic Methods for Text Classification},
Booktitle = {Association for Computational Linguistics},
Author = {Mohit Iyyer and Varun Manjunatha and Jordan Boyd-Graber and Hal {Daum\'{e} III}},
Year = {2015},
Location = {Beijing, China}
}

Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers.
Anupam Guha, Mohit Iyyer, Danny Bouman, and Jordan Boyd-Graber.
NAACL 2015

code + data // bibtex

@inproceedings{Guha:Iyyer:Bouman:Boyd-Graber-2015,
Title = {Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers.},
Author = {Anupam Guha and Mohit Iyyer and Danny Bouman and Jordan Boyd-Graber},
Booktitle = {North American Association for Computational Linguistics},
Year = {2015},
Location = {Denver, Colorado}
}

Generating Sentences from Semantic Vector Space Representations.
Mohit Iyyer, Jordan Boyd-Graber, and Hal Daumé III.
NIPS Workshop on Learning Semantics, 2014

bibtex

@inproceedings{Iyyer:Boyd-Graber:Daume-2014,
Title = {Generating Sentences from Semantic Vector Space Representations},
Author = {Mohit Iyyer and Jordan Boyd-Graber and Hal {Daum\'e III}},
Booktitle = {NIPS Workshop on Learning Semantics},
Year = {2014},
Location = {Montreal, Canada}
}

A Neural Network for Factoid Question Answering over Paragraphs.
Mohit Iyyer, Jordan Boyd-Graber, Leonardo Claudino, Richard Socher, and Hal Daumé III.
EMNLP 2014

code + data // bibtex // press: umiacs, terp, diamondback, colorado cs

@inproceedings{Iyyer:Boyd-Graber:Claudino:Socher:Daume-2014,
Title = {A Neural Network for Factoid Question Answering over Paragraphs},
Author = {Mohit Iyyer and Jordan Boyd-Graber and Leonardo Claudino and Richard Socher and Hal {Daum\'e III}},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = {2014},
Location = {Doha, Qatar},
}

Political Ideology Detection Using Recursive Neural Networks.
Mohit Iyyer, Peter Enns, Jordan Boyd-Graber, and Philip Resnik.
ACL 2014

data // bibtex

@inproceedings{Iyyer:Enns:Boyd-Graber:Resnik-2014,
Title = {Political Ideology Detection Using Recursive Neural Networks},
Author = {Mohit Iyyer and Peter Enns and Jordan Boyd-Graber and Philip Resnik},
Booktitle = {Association for Computational Linguistics},
Year = {2014},
Location = {Baltimore, Maryland},
}