Share This Author
From Recognition to Cognition: Visual Commonsense Reasoning
- Rowan Zellers, Yonatan Bisk, Ali Farhadi, Yejin Choi
- Computer ScienceComputer Vision and Pattern Recognition
- 27 November 2018
To move towards cognition-level understanding, a new reasoning engine is presented, Recognition to Cognition Networks (R2C), that models the necessary layered inferences for grounding, contextualization, and reasoning.
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
- Rowan Zellers, Yonatan Bisk, Roy Schwartz, Yejin Choi
- Computer ScienceConference on Empirical Methods in Natural…
- 16 August 2018
This paper introduces the task of grounded commonsense inference, unifying natural language inference and commonsense reasoning, and proposes Adversarial Filtering (AF), a novel procedure that constructs a de-biased dataset by iteratively training an ensemble of stylistic classifiers, and using them to filter the data.
Defending Against Neural Fake News
- Rowan Zellers, Ari Holtzman, Yejin Choi
- Computer ScienceNeural Information Processing Systems
- 29 May 2019
A model for controllable text generation called Grover, found that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data, and the best defense against Grover turns out to be Grover itself, with 92% accuracy.
ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks
- Mohit Shridhar, Jesse Thomason, D. Fox
- Computer ScienceComputer Vision and Pattern Recognition
- 3 December 2019
It is shown that a baseline model based on recent embodied vision-and-language tasks performs poorly on ALFRED, suggesting that there is significant room for developing innovative grounded visual language understanding models with this benchmark.
HellaSwag: Can a Machine Really Finish Your Sentence?
- Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, Yejin Choi
- Computer ScienceAnnual Meeting of the Association for…
- 1 May 2019
The construction of HellaSwag, a new challenge dataset, and its resulting difficulty, sheds light on the inner workings of deep pretrained models, and suggests a new path forward for NLP research, in which benchmarks co-evolve with the evolving state-of-the-art in an adversarial way, so as to present ever-harder challenges.
Synthetic and Natural Noise Both Break Neural Machine Translation
- Yonatan Belinkov, Yonatan Bisk
- Computer ScienceInternational Conference on Learning…
- 6 November 2017
It is found that a model based on a character convolutional neural network is able to simultaneously learn representations robust to multiple kinds of noise, including structure-invariant word representations and robust training on noisy texts.
PIQA: Reasoning about Physical Commonsense in Natural Language
- Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, Yejin Choi
- Computer ScienceAAAI Conference on Artificial Intelligence
- 26 November 2019
The task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA are introduced and analysis about the dimensions of knowledge that existing models lack are provided, which offers significant opportunities for future research.
Supertagging With LSTMs
- Ashish Vaswani, Yonatan Bisk, Kenji Sagae, Ryan Musa
- Computer ScienceNAACL
- 1 June 2016
This paper presents new state-of-the-art performance on CCG supertagging and parsing and demonstrates that while feed-forward architectures can compete with bidirectional LSTMs on POS tagging, models that encode the complete sentence are necessary for the long range syntactic information encoded in supertags.
Experience Grounds Language
- Yonatan Bisk, Ari Holtzman, Joseph P. Turian
- Computer ScienceConference on Empirical Methods in Natural…
- 21 April 2020
It is posited that the present success of representation learning approaches trained on large text corpora can be deeply enriched from the parallel tradition of research on the contextual and social nature of language.
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
- Liyiming Ke, Xiujun Li, S. Srinivasa
- Computer ScienceComputer Vision and Pattern Recognition
- 6 March 2019
We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the 2018 Room-to-Room (R2R)…
...
...