Home /
Research
Showing 547 - 552 / 897
Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling
ShrutiBhosale, KyraYee, SergeyEdunov....
Published date-11/13/2020
MachineTranslation
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
JinlanFu, PengFeiLiu, GrahamNeubig....
Published date-11/13/2020
NamedEntityRecognition
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
AliAlQallaf, GerardoAragon-Camarasa....
Published date-11/13/2020
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?
JinlanFu, PengFeiLiu, QiZhang....
Published date-11/13/2020
ChineseWordSegmentation
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
YuFeiWang, GauthamNarayanNarasimhan, XingyuLin....
Published date-11/13/2020
Multi-GoalReinforcementLearning
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 …
MateuszBuda, AshirbaniSaha, RuthWalsh....
Published date-11/13/2020
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 …