Yonatan Bisk – יונתן ביסק

About

Research

Github

CS Demographics

My research area is Natural Language Processing (NLP) with a focus on grounding. In particular, my work broadly falls into: 1. Uncovering the latent structures of natural language, 2. Modeling the semantics of the physical world, and 3. Connecting language to perception and control.

Fall 2020
Assistant Professor @ CMU
Language Technologies and Robotics Institutes

Previously
I received my PhD from the University of Illinois at Urbana-Champaign working with Julia Hockenmaier and my BS from the University of Texas at Austin, working with Risto Miikkulainen. I also did postdocs with Daniel Marcu at ISI and Yejin Choi at UW & AI2

ybisk ¯\_(ツ)_/¯ yonatanbisk.com
Instagram

News/Events:




PDFs ↓
BibTex ↓
Defending Against Neural Fake News [Demo]
Rowan Zellers, Ari Holtzman, Hannah Rashkin,
Yonatan Bisk
, Ali Farhadi, Franziska Roesner, Yejin Choi
Improving Robot Success Detection using Static Object Data [Video]
Rosario Scalise, Jesse Thomason,
Yonatan Bisk
, Siddhartha Srinivasa
FIND: Identifying Functionally and Structurally Important Features in Protein Sequences with Deep Neural Networks
Ranjani Murali, James Hemp, Victoria Orphan,
Yonatan Bisk

Early Fusion for Goal Directed Robotic Vision
Aaron Walsman,
Yonatan Bisk
, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox
HellaSwag: Can a Machine Really Finish Your Sentence?
ACL

Rowan Zellers, Ari Holtzman,
Yonatan Bisk
, Ali Farhadi, Yejin Choi
From Recognition to Cognition: Visual Commonsense Reasoning
Rowan Zellers,
Yonatan Bisk
, Ali Farhadi, Yejin Choi
Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation [Video]
Liyiming Ke, Xiujun Li,
Yonatan Bisk
, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, Siddhartha Srinivasa
Prospection: Interpretable Plans From Language By Predicting the Future
Chris Paxton,
Yonatan Bisk
, Jesse Thomason, Arunkumar Byravan, Dieter Fox
Shifting the Baseline: Single Modality Performance on Visual Navigation & QA
Jesse Thomason, Daniel Gordon,
Yonatan Bisk

Benchmarking Hierarchical Script Knowledge [Code]
Yonatan Bisk
, Jan Buys, Karl Pichotta, Yejin Choi
Character-based Surprisal as a Model of Reading Difficulty in the Presence of Errors
Michael Hahn, Frank Keller,
Yonatan Bisk
, Yonatan Belinkov
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference [Talk]
Rowan Zellers,
Yonatan Bisk
, Roy Schwartz, Yejin Choi
Inducing Grammars with and for Neural Machine Translation
Ke Tran,
Yonatan Bisk

Bridging HMMs and RNNs through Architectural Transformations
Jan Buys,
Yonatan Bisk
, Yejin Choi
Synthetic and Natural Noise Both Break Neural Machine Translation
Yonatan Belinkov,
Yonatan Bisk

CHALET: Cornell House Agent Learning Environment
Claudia Yan, Dipendra Misra, Andrew Bennnett, Aaron Walsman,
Yonatan Bisk
, Yoav Artzi
Learning Interpretable Spatial Operations in a Rich 3D Blocks World  [Poster]
Yonatan Bisk
, Kevin Shih, Yejin Choi, Daniel Marcu
Natural Language Inference from Multiple Premises [Data] [Slides] [Talk]
Alice Lai,
Yonatan Bisk
, Julia Hockenmaier
Natural Language Communication with Robots
Yonatan Bisk
, Deniz Yuret, Daniel Marcu
Supertagging with LSTMs [Talk]
Ashish Vaswani,
Yonatan Bisk
, Kenji Sagae, Ryan Musa
Towards a Dataset for Human Computer Communication via Grounded Language Acquisition
Yonatan Bisk
, Daniel Marcu, William Wong
Unsupervised Neural Hidden Markov Models  [Slides]
Ke Tran,
Yonatan Bisk
, Ashish Vaswani, Daniel Marcu, Kevin Knight
Evaluating Induced CCG Parsers on Grounded Semantic Parsing
Yonatan Bisk
, Siva Reddy, John Blitzer, Julia Hockenmaier, Mark Steedman
Probing the Linguistic Strengths and Limitations of Unsupervised Grammar Induction [Talk]
Yonatan Bisk
, Julia Hockenmaier
Labeled Grammar Induction with Minimal Supervision  [Poster]
Yonatan Bisk
, Christos Christodoulopoulos, Julia Hockenmaier
An HDP Model for Inducing Combinatory Categorial Grammars [Slides] [Talk]
Yonatan Bisk
, Julia Hockenmaier
Simple Robust Grammar Induction with Combinatory Categorial Grammar
Yonatan Bisk
, Julia Hockenmaier
Document-Topic Hierarchies from Document Graphs
Tim Weninger,
Yonatan Bisk
, Jiawei Han
Induction of Linguistic Structure with Combinatory Categorial Grammars
Yonatan Bisk
, Julia Hockenmaier
Normal-form parsing for CCGs with generalized composition and type-raising
Julia Hockenmaier,
Yonatan Bisk


Theses

2015
Unsupervised Grammar Induction with Combinatory Categorial Grammars
Advised by Julia Hockenmaier
Committee: Jason Eisner, Dan Roth, Cheng Zhai

2009
The Necessity of Separating Control and Logic When Grounding Language using Neuroevolution
Undergraduate Thesis Advised by Risto Miikkulainen