Results 1 to 10 of about 914,128 (308)
Improving Abstraction in Text Summarization [PDF]
Conference on Empirical Methods in Natural Language Processing, 2018 ive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document.
Kryściński, Wojciech +3 more
core +2 more sources
“What It Wants Me To Say”: Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models [PDF]
International Conference on Human Factors in Computing Systems, 2023 Code-generating large language models map natural language to code. However, only a small portion of the infinite space of naturalistic utterances is effective at guiding code generation.
Michael Xieyang Liu +6 more
semanticscholar +1 more source
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection [PDF]
International Journal of Computer Vision, 2021 3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields. In this paper, we propose Point-Voxel Region-based Convolution Neural Networks (PV-RCNNs) for 3D object detection on ...
Shaoshuai Shi +7 more
semanticscholar +1 more source
Abstraction and analogy‐making in artificial intelligence [PDF]
Annals of the New York Academy of Sciences, 2021 Conceptual abstraction and analogy‐making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains.
M. Mitchell
semanticscholar +1 more source
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection [PDF]
Computer Vision and Pattern Recognition, 2019 We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.
Shaoshuai Shi +6 more
semanticscholar +1 more source
Multi-Agent Game Abstraction via Graph Attention Neural Network [PDF]
AAAI Conference on Artificial Intelligence, 2019 In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue.
Y. Liu +5 more
semanticscholar +1 more source
Event abstraction in process mining: literature review and taxonomy
Granular Computing, 2020 The execution of processes in companies generates traces of event data, stored in the underlying information system(s), capturing the actual execution of the process.
Sebastiaan J. van Zelst +3 more
semanticscholar +1 more source
Abstraction of Observables [PDF]
, 2012 Making use of the laws of physical transactions, we study symmetrical many-points systems. Relation of group-theory to physical transactions in such symmetrical systems is dealt with.
Ganguly, Subhajit
core +1 more source
Genome Biology, 2019 Single-cell RNA-seq quantifies biological heterogeneity across both discrete cell types and continuous cell transitions. Partition-based graph abstraction (PAGA) provides an interpretable graph-like map of the arising data manifold, based on estimating ...
F. A. Wolf +8 more
semanticscholar +1 more source
Fairness and Abstraction in Sociotechnical Systems
FAT, 2019 A key goal of the fair-ML community is to develop machine-learning based systems that, once introduced into a social context, can achieve social and legal outcomes such as fairness, justice, and due process. Bedrock concepts in computer science---such as
Andrew D. Selbst +4 more
semanticscholar +1 more source