The Role of Massively Multi-Task and Weak Supervision in Software 2.0
Explore this paper's citation graph
Summary
A vision for a Software 2.0 lifecycle centered around the idea that labeling training data can be the primary interface to Software 2.0 systems is outlined, and an interim report on Snorkel, the prototype Software 2.0 system is provided.
- Type
- article
- Published
- 2019-01-01
- Cited by
- 29
- References
- 48
- OpenAlex
- https://openalex.org/W2911450016
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:53456226
Keywords
Computer science, Task (project management), Massively parallel, Software, Software engineering
References
- Maximum Likelihood Estimation of Observer Error‐Rates Using the EM Algorithm
- Snuba: Automating Weak Supervision to Label Training Data
- Aggregating crowdsourced binary ratings
- Distilling the Knowledge in a Neural Network
- Distant supervision for relation extraction without labeled data
- Pattern Learning for Relation Extraction with a Hierarchical Topic Model
- Consistency of weighted majority votes
- Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations
- A Survey on Transfer Learning
- Deep Residual Learning for Image Recognition
- Model compression
- Deep multi-task learning with low level tasks supervised at lower layers
- The microsoft 2016 conversational speech recognition system
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- Constrained Deep Weak Supervision for Histopathology Image Segmentation
- HoloClean: Holistic Data Repairs with Probabilistic Inference
- Learning the Structure of Generative Models without Labeled Data
- Neural Ranking Models with Weak Supervision
- An Overview of Multi-Task Learning in Deep Neural Networks
- One Model To Learn Them All
Cited by
- Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices
- Ludwig: a type-based declarative deep learning toolbox
- A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective
- The Importance of Imaging Informatics and Informaticists in the Implementation of AI.
- Panorama: A Data System for Unbounded Vocabulary Querying over Video
- Migrating a Privacy-Safe Information Extraction System to a Software 2.0 Design
- Med7: a transferable clinical natural language processing model for electronic health records
- Slice Tuner: A Selective Data Collection Framework for Accurate and Fair Machine Learning Models
- Overton: A Data System for Monitoring and Improving Machine-Learned Products
- Machine Learning Systems for Intelligent Services in the IoT: A Survey.
- Influence of Artificial Intelligence on Personalized Medical Predictions, Interventions and Quality of Life Issues
- AHMoSe: A Knowledge-Based Visual Support System for Selecting Regression Machine Learning Models
- Large-Scale Counting and Localization of Pineapple Inflorescence Through Deep Density-Estimation
- Multi-task weak supervision enables anatomically-resolved abnormality detection in whole-body FDG-PET/CT
- Two-dimensional predictive model: Data analysis using regression algorithm
- Exploring Inspiration Sets in a Data Programming Pipeline for Product Moderation
- Heterogeneous Multi-Source Deep Adaptive Knowledge-Aware Learning for E-Mobility
- A text analysis model based on Probabilistic-KG
- To be forgotten or to be fair: unveiling fairness implications of machine unlearning methods
- Rock: Cleaning Data by Embedding ML in Logic Rules
Related papers
- Snorkel: Rapid Training Data Creation with Weak Supervision
- The Four-Second Supervisor: Multi-Tasking Supervision and Its Support
- Task management principles for e-learning environments
- Errata to "On-Edge Multi-Task Transfer Learning: Model and Practice With Data-Driven Task Allocation"
- Task-role-based access control in distributed collaborative system
- A Collaborative Relevance Feedback Approach to Task-driven Recommendation
- Task orientation of human-machine interaction in distributed systems
- Collaborative Management System Driven by Task Flow in Supercomputing Environment