Home /
Research
Showing 817 - 822 / 904
WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization
MdTahmidRahmanLaskar, EnamulHoque, JimmyXiangjiHuang....
Published date-11/03/2020
AbstractiveTextSummarization, DocumentSummarization, Multi-DocumentSummarization
In the Query Focused Multi-Document Summarization (QF-MDS) task, a set of documents and a query are given where the goal is to generate a summary from these documents based on …
BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger
HarshPatel....
Published date-11/03/2020
InformationRetrieval, NamedEntityRecognition
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 …
Amortized Variational Deep Q Network
HaotianZhang, YuhaoWang, JianyongSun....
Published date-11/03/2020
EfficientExploration, OpenAIGym, VariationalInference
Efficient exploration is one of the most important issues in deep reinforcement learning. To address this issue, recent methods consider the value function parameters as random variables, and resort variational …
The Complexity of Gradient Descent: CLS = PPAD $\cap$ PLS
JohnFearnley, PaulW.Goldberg, AlexandrosHollender....
Published date-11/03/2020
We study search problems that can be solved by performing Gradient Descent on a bounded convex polytopal domain and show that this class is equal to the intersection of two …
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
HuHu, Chao-HanHuckYang, XianjunXia....
Published date-11/03/2020
AcousticSceneClassification, DataAugmentation, SceneClassification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is …
Generalization to New Actions in Reinforcement Learning
AyushJain, AndrewSzot, JosephJ.Lim....
Published date-11/03/2020
A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes …