To make Sequential Recommendation (SR) successful, recent works focus on...
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative questi...
The distribution gap between training datasets and data encountered in
p...
We propose Dynamic Blocking, a decoding algorithm which enables large-sc...
Class-conditional language models (CC-LMs) can be used to generate natur...
Neural text decoding is important for generating high-quality texts usin...
Some consider large-scale language models that can generate long and coh...
Classical results on the statistical complexity of linear models have
co...
Large-scale language models show promising text generation capabilities,...
The paradigm of pretrained deep learning models has recently emerged in
...
Text summarization aims at compressing long documents into a shorter for...
While natural language processing systems often focus on a single langua...
Even as pre-trained language encoders such as BERT are shared across man...
End-to-end neural models have made significant progress in question
answ...
The convergence rate and final performance of common deep learning model...
While it has not yet been proven, empirical evidence suggests that model...
Deep learning has improved performance on many natural language processi...
Mode connectivity is a recently introduced frame- work that empirically
...
Many of the leading approaches in language modeling introduce novel, com...
Despite superior training outcomes, adaptive optimization methods such a...
State-of-the-art results on neural machine translation often use attenti...
Recurrent neural networks (RNNs), such as long short-term memory network...
Recurrent Neural Networks (RNNs) are powerful models that achieve except...