Incidental Supervision: Moving beyond Supervised Learning

2020/05/25 by Dan Roth, Roth, Dan · 4 citations
Computer Science · Biochemistry, Genetics and Molecular Biology · #Topic Modeling #Natural Language Processing Techniques #Biomedical Text Mining and Ontologies

paper · pdf · doi:10.48550/arxiv.2005.12339

Abstract

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on it. However, learning models for these tasks is difficult partly because generating the necessary supervision signals for it is costly and does not scale. This paper describes several learning paradigms that are designed to alleviate the supervision bottleneck. It will illustrate their benefit in the context of multiple problems, all pertaining to inducing various levels of semantic representations from text.

Cited by

• QuASE: Question-Answer Driven Sentence Encoding
• Combining Probabilistic Logic and Deep Learning for Self-Supervised Learning
• Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
• Cross-lingual Entity Alignment with Incidental Supervision
• Learning Constraints and Descriptive Segmentation for Subevent Detection
• Self-supervised self-supervision by combining deep learning and probabilistic logic
• Zero-Shot Open Entity Typing as Type-Compatible Grounding

Related

• Task Bias in Vision-Language Models
• How to Train Text Summarization Model with Weak Supervisions
• Weakly Supervised Text Classification using Supervision Signals from a Language Model
• Tailoring Self-Supervision for Supervised Learning
• Language Models in the Loop: Incorporating Prompting into Weak Supervision