Home /

Research

Showing 685 - 690 / 897

Explaining Deep Graph Networks with Molecular Counterfactuals


Authors:  DaniloNumeroso, DavideBacciu....
Published date-11/09/2020

Abstract: We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations …

Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE


Authors:  DingZhou, Xue-XinWei....
Published date-11/09/2020
Tasks:  LatentVariableModels

Abstract: The ability to record activities from hundreds of neurons simultaneously in the brain has placed an increasing demand for developing appropriate statistical techniques to analyze such data. Recently, deep generative …

Chapter Captor: Text Segmentation in Novels


Authors:  CharutaPethe, AllenKim, StevenSkiena....
Published date-11/09/2020

Abstract: Books are typically segmented into chapters and sections, representing coherent subnarratives and topics. We investigate the task of predicting chapter boundaries, as a proxy for the general task of segmenting …

Nanopore Base Calling on the Edge


Authors:  PeterPerešíni, VladimírBoža, BroňaBrejová....
Published date-11/09/2020
Tasks:  SpeechRecognition

Abstract: We developed a new base caller DeepNano-coral for nanopore sequencing, which is optimized to run on the Coral Edge Tensor Processing Unit, a small USB-attached hardware accelerator. To achieve this …

RMITB at TREC COVID 2020


Authors:  RodgerBenham, AlistairMoffat, J.ShaneCulpepper....
Published date-11/09/2020

Abstract: Search engine users rarely express an information need using the same query, and small differences in queries can lead to very different result sets. These user query variations have been …

"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL


Authors:  YuntaoLi, BeiChen, QianLiu....
Published date-11/09/2020
Tasks:  Text-To-Sql

Abstract: In Natural Language Interfaces to Databases systems, the text-to-SQL technique allows users to query databases by using natural language questions. Though significant progress in this area has been made recently, …

Filter by

Categories

Tags