Home /

Research

Showing 889 - 894 / 897

Combining Event Semantics and Degree Semantics for Natural Language Inference

Authors:  IzumiHaruta, KojiMineshima, DaisukeBekki....
Published date-11/02/2020
Tasks:  NaturalLanguageInference

Abstract: In formal semantics, there are two well-developed semantic frameworks: event semantics, which treats verbs and adverbial modifiers using the notion of event, and degree semantics, which analyzes adjectives and comparatives …
Paper Code

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation

Authors:  RuizheLi, XiaoLi, GuanyiChen....
Published date-11/02/2020
AutoEncoder
Generative Models
VAE
Tasks:  LanguageModelling, TextGeneration

Abstract: 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 …
Paper Code

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

Authors:  JianGuo, HeHe, TongHe....
Published date-07/09/2020
Computer Vision
CV
GluonCV
GluonNLP

Abstract: We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and …
Paper Code

SqueezeBERT: What can computer vision teach NLP about efficient neural networks?

Authors:  ForrestN.Iandola, AlbertE.Shaw, RaviKrishna....
Published date-06/19/2020
computer
vision
Tasks:  LINGUISTICACCEPTABILITY, NATURALLANGUAGEINFERENCE, SENTIMENTANALYSIS, TRANSFERLEARNING

Abstract: Humans read and write hundreds of billions of messages every day. Further, due to the availability of large datasets, large computing systems, and better neural network models, natural language processing …
Paper Code

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Authors:  EdgarRiba, DmytroMishkin, DanielPonsa....
Published date-10/05/2019
computer
vision
Tasks:  edgedetection

Abstract: This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. The package uses …
Paper Code

UnrealCV: Connecting Computer Vision to Unreal Engine

Authors:  WeichaoQiu, AlanYuille....
Published date-09/05/2019
UnrealCV
Unreal Engine 4
virtual world
Tasks:  physicalsimulations

Abstract: Computer graphics can not only generate synthetic images and ground truth but it also offers the possibility of constructing virtual worlds in which: (i) an agent can perceive, navigate, and …
Paper Code

Filter by

Categories

Tags