Home /

Research

Showing 547 - 552 / 897

Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling


Authors:  ShrutiBhosale, KyraYee, SergeyEdunov....
Published date-11/13/2020
Tasks:  MachineTranslation

Abstract: Pre-training models on vast quantities of unlabeled data has emerged as an effective approach to improving accuracy on many NLP tasks. On the other hand, traditional machine translation has a …

Interpretable Multi-dataset Evaluation for Named Entity Recognition


Authors:  JinlanFu, PengFeiLiu, GrahamNeubig....
Published date-11/13/2020
Tasks:  NamedEntityRecognition

Abstract: With the proliferation of models for natural language processing tasks, it is even harder to understand the differences between models and their relative merits. Simply looking at differences between holistic …

Enabling the Sense of Self in a Dual-Arm Robot


Authors:  AliAlQallaf, GerardoAragon-Camarasa....
Published date-11/13/2020

Abstract: While humans are aware of their body and capabilities, robots are not. To address this, we present in this paper a neural network architecture that enables a dual-arm robot to …

RethinkCWS: Is Chinese Word Segmentation a Solved Task?


Authors:  JinlanFu, PengFeiLiu, QiZhang....
Published date-11/13/2020
Tasks:  ChineseWordSegmentation

Abstract: The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models. …

ROLL: Visual Self-Supervised Reinforcement Learning with Object Reasoning


Authors:  YuFeiWang, GauthamNarayanNarasimhan, XingyuLin....
Published date-11/13/2020
Tasks:  Multi-GoalReinforcementLearning

Abstract: Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning. This leads to inefficient goal sampling and ineffective reward functions. In this paper, we …

Detection of masses and architectural distortions in digital breast tomosynthesis: a publicly available dataset of 5,060 patients and a deep …


Authors:  MateuszBuda, AshirbaniSaha, RuthWalsh....
Published date-11/13/2020

Abstract: Breast cancer screening is one of the most common radiological tasks with over 39 million exams performed each year. While breast cancer screening has been one of the most studied …

Filter by

Categories

Tags