There exist features that are related to the label in the same way acros...
Large language models (LLMs) have shown remarkable reasoning capabilitie...
In-context learning (ICL) suffers from oversensitivity to the prompt, wh...
Recent work has found that multi-task training with a large number of di...
Noisy channel models have been especially effective in neural machine
tr...
To enable building and testing models on long-document comprehension, we...
Machine-in-the-loop writing aims to enable humans to collaborate with mo...
The goal of meta-learning is to learn to adapt to a new task with only a...
Despite agreement on the importance of detecting out-of-distribution (OO...
Despite recent progress in abstractive summarization, systems still suff...
While pretrained language models achieve excellent performance on natura...
Unsupervised approaches to extractive summarization usually rely on a no...
Current approaches to text generation largely rely on autoregressive mod...
Recent work has shown that pre-trained language models such as BERT impr...
Neural abstractive summarization models are prone to generate content
in...
A brain-computer interface (BCI) system usually needs a long calibration...
A brain-computer interface (BCI) system usually needs a long calibration...
Negotiation is a complex activity involving strategic reasoning, persuas...
Statistical natural language inference (NLI) models are susceptible to
l...
Multi-view learning improves the learning performance by utilizing multi...
We present GluonCV and GluonNLP, the deep learning toolkits for computer...
We tackle the problem of generating a pun sentence given a pair of homop...
Quizbowl is a scholastic trivia competition that tests human knowledge a...
We consider negotiation settings in which two agents use natural languag...
We present QuAC, a dataset for Question Answering in Context that contai...
Almost all EEG-based brain-computer interfaces (BCIs) need some labeled
...
The electroencephalogram (EEG) is the most widely used input for brain
c...
The electroencephalogram (EEG) is the most popular form of input for bra...
We know very little about how neural language models (LM) use prior
ling...
We consider the task of text attribute transfer: transforming a sentence...
We study a symmetric collaborative dialogue setting in which two agents,...
We propose a general framework for sequential and dynamic acquisition of...
We demonstrate that a dependency parser can be built using a credit
assi...