Yonatan Bisk – יונתן ביסק

About

Research

Github

CS Demographics

[CV][Google Scholar]

Preprints
From Recognition to Cognition: Visual Commonsense Reasoning
ArXiv
      Rowan Zellers,
Yonatan Bisk
, Ali Farhadi, Yejin Choi
[bib]

Early Fusion for Goal Directed Robotic Vision
ArXiv
      Aaron Walsman,
Yonatan Bisk
, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox
[bib]

Shifting the Baseline: Single Modality Performance on Visual Navigation & QA
ArXiv
      Jesse Thomason, Daniel Gordon, and
Yonatan Bisk
[bib]

2018 SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
EMNLP
      Rowan Zellers,
Yonatan Bisk
, Roy Schwartz and Yejin Choi
[bib]

Inducing Grammars with and for Neural Machine Translation
Wksp on NMT (best paper)
      Ke Tran and
Yonatan Bisk
[bib]

Bridging HMMs and RNNs through Architectural Transformations
IRASL wksp @ NeurIPS
      Jan Buys,
Yonatan Bisk
, and Yejin Choi
[bib]

Synthetic and Natural Noise Both Break Neural Machine Translation
ICLR (oral)

      Yonatan Belinkov and
Yonatan Bisk
[bib]

CHALET: Cornell House Agent Learning Environment
Tech Report

      Claudia Yan, Dipendra Misra, Andrew Bennnett, Aaron Walsman,
Yonatan Bisk
& Yoav Artzi
[bib]

Learning Interpretable Spatial Operations in a Rich 3D Blocks World
AAAI

      
Yonatan Bisk
, Kevin Shih, Yejin Choi and Daniel Marcu
[Poster] [bib]

2017 Natural Language Inference from Multiple Premises
IJCNLP (oral)
      Alice Lai,
Yonatan Bisk
, and Julia Hockenmaier
[bib]

2016 Natural Language Communication with Robots
NAACL (oral)
      
Yonatan Bisk
, Deniz Yuret, and Daniel Marcu
[Data] [Slides] [Video] [bib]

      A dataset & models for isolating difficulties in language grounding
Supertagging with LSTMs
NAACL Short (oral)

      Ashish Vaswani,
Yonatan Bisk
, Kenji Sagae, and Ryan Musa
[Video] [bib]

      Supertagging performance and errors correlate with conditioning context
Towards a Dataset for Human Computer Communication via Grounded Language Acquisition
      
Yonatan Bisk
, Daniel Marcu and William Wong
Wksp on Symbolic Cognitive Systems [bib]

Unsupervised Neural Hidden Markov Models
Structure Pred Wksp (oral)

      Ke Tran,
Yonatan Bisk
, Ashish Vaswani, Daniel Marcu, and Kevin Knight
[Slides] [bib]

      EM style training of unsupervised HMM with neural networks
Evaluating Induced CCG Parsers on Grounded Semantic Parsing
EMNLP

      
Yonatan Bisk
, Siva Reddy, John Blitzer, Julia Hockenmaier and Mark Steedman
[bib]

      A dataset & evaluation for semantic parsing using induced grammars
2015 Probing the Linguistic Strengths and Limitations of Unsupervised Grammar Induction
ACL (oral)
      
Yonatan Bisk
and Julia Hockenmaier
[Video] [bib]

      Unsupervised Labeled dependencies and Analysis
Labeled Grammar Induction with Minimal Supervision
ACL Short

      
Yonatan Bisk
, Christos Christodoulopoulos and Julia Hockenmaier
[Poster] [bib]

      Induced clusters get you 70% of the performance you get from gold tags. (*Table 3 corrected)
2013 An HDP Model for Inducing Combinatory Categorial Grammars
TACL Vol 1.
      
Yonatan Bisk
and Julia Hockenmaier
[Slides] [Video] [bib]

      Parameter Sharing is essential to unsupervised performance
2012 Simple Robust Grammar Induction with Combinatory Categorial Grammar
AAAI
      
Yonatan Bisk
and Julia Hockenmaier
[bib]

      A CCG Grammar can be automatically induced from nouns and verbs
Document-Topic Hierarchies from Document Graphs
CIKM

      Tim Weninger,
Yonatan Bisk
, and Jiawei Han
[bib]

Induction of Linguistic Structure with Combinatory Categorial Grammars
      
Yonatan Bisk
and Julia Hockenmaier
Wksp on Inducing Linguistic Structure

      [Corrected PASCAL Overview Paper] [Corrected Challenge Results]
[bib]

2010 Normal-form parsing for CCGs with generalized composition and type-raising
Coling
      Julia Hockenmaier and
Yonatan Bisk
[bib]

      Appropriately restricting Type-Raising and Composition greatly reduces ambiguity


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


What is CCG?

Sadly there is no good intro to CCG that is geared at Computer Scientists that I'm aware of, but hopefully a coherent picture can be constructed without too much effort from the following links:
My Thesis: Chapter 3
Mark Steedman's CCG Page and NASSLI Tutorial or for the adventurous: The Syntactic Process