research
∙
05/18/2023
Language Models Meet World Models: Embodied Experiences Enhance Language Models
While large language models (LMs) have shown remarkable capabilities acr...
share
research
∙
04/08/2023
FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement
With the increasing data volume, there is a trend of using large-scale p...
research
∙
08/01/2022
Composable Text Control Operations in Latent Space with Ordinary Differential Equations
Real-world text applications often involve composing a wide range of tex...
research
∙
05/12/2022
TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding
Data augmentation is an effective approach to tackle over-fitting. Many ...
research
∙
12/29/2021
Dense-to-Sparse Gate for Mixture-of-Experts
Mixture-of-experts (MoE) is becoming popular due to its success in impro...
research
∙
06/29/2021
Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation
Neural text generation models are typically trained by maximizing log-li...
research
∙
10/04/2020
Local Additivity Based Data Augmentation for Semi-supervised NER
Named Entity Recognition (NER) is one of the first stages in deep langua...
research
∙
06/28/2020
Progressive Generation of Long Text
Large-scale language models pretrained on massive corpora of text, such ...
research
∙
04/25/2020
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
This paper presents MixText, a semi-supervised learning method for text ...
research
∙
11/10/2019
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
Deep learning has revolutionized speech recognition, image recognition, ...
research
∙
01/28/2019
Toward Unsupervised Text Content Manipulation
Controlled generation of text is of high practical use. Recent efforts h...
research
∙
11/24/2018
Connecting the Dots Between MLE and RL for Sequence Generation
Sequence generation models such as recurrent networks can be trained wit...
research
∙
09/04/2018
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
We introduce Texar, an open-source toolkit aiming to support the broad s...
research
∙
06/26/2018
Deep Generative Models with Learnable Knowledge Constraints
The broad set of deep generative models (DGMs) has achieved remarkable a...
research
∙
05/30/2018
Unsupervised Text Style Transfer using Language Models as Discriminators
Binary classifiers are often employed as discriminators in GAN-based uns...
research
∙
06/02/2017
On Unifying Deep Generative Models
Deep generative models have achieved impressive success in recent years....
research
∙
03/02/2017
Toward Controlled Generation of Text
Generic generation and manipulation of text is challenging and has limit...
research
∙
02/27/2017
Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
Recent work on generative modeling of text has found that variational au...
research
∙
11/05/2016
Reference-Aware Language Models
We propose a general class of language models that treat reference as an...
research
∙
07/18/2016
Neural Machine Translation with Recurrent Attention Modeling
Knowing which words have been attended to in previous time steps while g...
research
∙
11/07/2015
Stacked Attention Networks for Image Question Answering
This paper presents stacked attention networks (SANs) that learn to answ...
research
∙
12/22/2014
Deep Fried Convnets
The fully connected layers of a deep convolutional neural network typica...
research
∙
12/19/2014