Skip to search formSkip to main contentSkip to account menu
The Curious Case of Neural Text Degeneration
TLDR
By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence.
View PDF on arXiv
Defending Against Neural Fake News
TLDR
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.
View PDF on arXiv
HellaSwag: Can a Machine Really Finish Your Sentence?
TLDR
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.
View on ACL
Abductive Commonsense Reasoning
TLDR
This study introduces a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations, and conceptualizes two new tasks -- Abductive NLI: a multiple-choice question answering task for choosing the more likely explanation, and Abduction NLG: a conditional generation task for explaining given observations in natural language.
View PDF on arXiv
Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
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)…
View on IEEE
Simulating Action Dynamics with Neural Process Networks
TLDR
This work introduces Neural Process Networks to understand procedural text through (neural) simulation of action dynamics, and complements existing memory architectures with dynamic entity tracking by explicitly modeling actions as state transformers.
View PDF on arXiv
Experience Grounds Language
TLDR
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.
View on ACL
Learning to Write with Cooperative Discriminators
TLDR
Human evaluation demonstrates that text generated by the unified learning framework is preferred over that of baselines by a large margin, significantly enhancing the overall coherence, style, and information of the generations.
View on ACL
Counterfactual Story Reasoning and Generation
TLDR
This paper proposes Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactually event.
View on ACL
Connotation Frames of Power and Agency in Modern Films
TLDR
This work uses connotation frames of power and agency frames to measure the subtle, but prevalent, gender bias in the portrayal of modern film characters and provide insights that deviate from the well-known Bechdel test.
View on ACL
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License