Home /

Research

Showing 829 - 834 / 897

SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation


Authors:  XutaiMa, JuanPino, PhilippKoehn....
Published date-11/03/2020

Abstract: Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together. We investigate how to adapt simultaneous text translation methods such …

Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems


Authors:  StéphanedAscoli, AliceCoucke, FrancescoCaltagirone....
Published date-11/03/2020
Tasks:  DataAugmentation, LanguageModelling, Task-OrientedDialogueSystems, TextGeneration

Abstract: Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely …

Towards a Universal Gating Network for Mixtures of Experts


Authors:  ChenWenKang, ChuaMengHong, TomasMaul....
Published date-11/03/2020

Abstract: The combination and aggregation of knowledge from multiple neural networks can be commonly seen in the form of mixtures of experts. However, such combinations are usually done using networks trained …

Shift If You Can: Counting and Visualising Correction Operations for Beat Tracking Evaluation


Authors:  A.SáPinto, I.Domingues, M.E.P.Davies....
Published date-11/03/2020

Abstract: In this late-breaking abstract we propose a modified approach for beat tracking evaluation which poses the problem in terms of the effort required to transform a sequence of beat detections …

The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets


Authors:  VidKocijan, Oana-MariaCamburu, ThomasLukasiewicz....
Published date-11/03/2020
Tasks:  CoreferenceResolution

Abstract: Diagnostic datasets that can detect biased models are an important prerequisite for bias reduction within natural language processing. However, undesired patterns in the collected data can make such tests incorrect. …

BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger


Authors:  HarshPatel....
Published date-11/03/2020
Tasks:  InformationRetrieval, NamedEntityRecognition

Abstract: Motivation: The proliferation of Biomedical research articles has made the task of information retrieval more important than ever. Scientists and Researchers are having difficulty in finding articles that contain information …

Filter by

Categories

Tags