Natural Language Feedback (NLF) is an increasingly popular avenue to ali...
Memory editing methods for updating encyclopedic knowledge in transforme...
An important aspect of developing LLMs that interact with humans is to a...
Representing texts as information about entities has long been deemed
ef...
Despite their unprecedented success, even the largest language models ma...
Like people, LLMs do not always generate the best text for a given gener...
Conditional set generation learns a mapping from an input sequence of to...
Large LMs such as GPT-3, while powerful, are not immune to mistakes, but...
How can an end-user provide feedback if a deployed structured prediction...
How can an end-user provide feedback if a deployed structured prediction...
A class of explainable NLP models for reasoning tasks support their deci...
Scripts - standardized event sequences describing typical everyday activ...
We present a new knowledge-base of hasPart relationships, extracted from...
Our goal is to better comprehend procedural text, e.g., a paragraph abou...
We introduce WIQA, the first large-scale dataset of "What if..." questio...
AI has achieved remarkable mastery over games such as Chess, Go, and Pok...
With the rise in popularity of social media, images accompanied by conte...
The social media explosion has populated the Internet with a wealth of
i...
Our goal is procedural text comprehension, namely tracking how the prope...
Comprehending procedural text, e.g., a paragraph describing photosynthes...
We present a new dataset and models for comprehending paragraphs about
p...
Our goal is to answer questions about paragraphs describing processes (e...
Learning a joint language-visual embedding has a number of very appealin...
Audio Description (AD) provides linguistic descriptions of movies and al...
Descriptive video service (DVS) provides linguistic descriptions of movi...