Machine Learning with World Knowledge: The Position and Survey
arXiv:1705.02908
Abstract
Machine learning has become pervasive in multiple domains, impacting a wide variety of applications, such as knowledge discovery and data mining, natural language processing, information retrieval, computer vision, social and health informatics, ubiquitous computing, etc. Two essential problems of machine learning are how to generate features and how to acquire labels for machines to learn. Particularly, labeling large amount of data for each domain-specific problem can be very time consuming and costly. It has become a key obstacle in making learning protocols realistic in applications. In this paper, we will discuss how to use the existing general-purpose world knowledge to enhance machine learning processes, by enriching the features or reducing the labeling work. We start from the comparison of world knowledge with domain-specific knowledge, and then introduce three key problems in using world knowledge in learning processes, i.e., explicit and implicit feature representation, inference for knowledge linking and disambiguation, and learning with direct or indirect supervision. Finally we discuss the future directions of this research topic.
References in corpus (12)
- Natural Language Processing (almost) from Scratch
- Probabilistic Latent Semantic Analysis
- A Review of Relational Machine Learning for Knowledge Graphs
- Zero-Shot Learning Through Cross-Modal Transfer
- End-To-End Memory Networks
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Harnessing Deep Neural Networks with Logic Rules
- A Neural Knowledge Language Model
- Search-based Structured Prediction
- A Restricted Visual Turing Test for Deep Scene and Event Understanding
- Estimation from Indirect Supervision with Linear Moments
- Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence