Skip to search formSkip to main contentSkip to account menu

Unsupervised Learning of Video Representations using LSTMs

This work uses Long Short Term Memory networks to learn representations of video sequences and evaluates the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.
View PDF on arXiv (opens in a new tab)

Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

The proposed conditional non-autoregressive neural sequence model is evaluated on machine translation and image caption generation, and it is observed that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.
View on ACL (opens in a new tab)

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

This work proposes to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature with trust region, which is the first scalable trust region natural gradient method for actor-critic methods.
View PDF on arXiv (opens in a new tab)

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System

This study presents PPTOD, a unified plug-and-play model for task-oriented dialogue, and introduces a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora.
View on ACL (opens in a new tab)

Generating Images from Captions with Attention

It is demonstrated that the proposed model produces higher quality samples than other approaches and generates images with novel scene compositions corresponding to previously unseen captions in the dataset.
View PDF on arXiv (opens in a new tab)

Molecular Geometry Prediction using a Deep Generative Graph Neural Network

A conditional deep generative graph neural network that learns an energy function by directly learning to generate molecular conformations that are energetically favorable and more likely to be observed experimentally in data-driven manner is proposed.
View on Springer (opens in a new tab)

A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models

The proposed framework models the process of generation rather than the resulting sequence, and under this framework, various neural sequence models are derived as special cases, such as autoregressive, semi-autorgressive, and refinement-based non-autoregressive models, which enables to adapt decoding algorithms originally developed for directed sequence models to undirected sequence models.
View PDF on arXiv (opens in a new tab)

Masked graph modeling for molecule generation

A graph- based molecular generative model that outperforms previously proposed graph-based generative models of molecules and performs comparably to several SMILES-based models is proposed.
View on Springer (opens in a new tab)

Initialization Strategies of Spatio-Temporal Convolutional Neural Networks

We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Temporal ConvNets…
View PDF on arXiv (opens in a new tab)

Capturing document context inside sentence-level neural machine translation models with self-training

This work proposes an approach that doesn’t require training a specialized model on parallel document-level corpora and is applied to a trained sentence-level NMT model at decoding time and demonstrates that it has higher BLEU score and higher human preference than the baseline.
View on ACL (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)