Home /
Research
Showing 889 - 894 / 904
Image Inpainting with Learnable Feature Imputation
HåkonHukkelås, FrankLindseth, RudolfMester....
Published date-11/02/2020
ImageInpainting, Imputation
A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image. Several studies address this issue with feature …
Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
RuizheLi, XiaoLi, GuanyiChen....
Published date-11/02/2020
LanguageModelling, TextGeneration
The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens …
Liputan6: A Large-scale Indonesian Dataset for Text Summarization
FajriKoto, JeyHanLau, TimothyBaldwin....
Published date-11/02/2020
AbstractiveTextSummarization, TextSummarization
In this paper, we introduce a large-scale Indonesian summarization dataset. We harvest articles from Liputan6.com, an online news portal, and obtain 215,827 document-summary pairs. We leverage pre-trained language models to …
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
HangLe, JuanPino, ChanghanWang....
Published date-11/02/2020
SpeechRecognition
We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani …
Adapting Pretrained Transformer to Lattices for Spoken Language Understanding
Chao-WeiHuang, Yun-NungChen....
Published date-11/02/2020
NaturalLanguageUnderstanding, SpeechRecognition, SpokenLanguageUnderstanding
Lattices are compact representations that encode multiple hypotheses, such as speech recognition results or different word segmentations. It is shown that encoding lattices as opposed to 1-best results generated by …
Toward a Generalization Metric for Deep Generative Models
HoangThanh-Tung, TruyenTran....
Published date-11/02/2020
Measuring the generalization capacity of Deep Generative Models (DGMs) is difficult because of the curse of dimensionality. Evaluation metrics for DGMs like Inception Score, Frechet Inception Distance, Precision-Recall, and Neural …