Accession Number:

AD1168008

Title:

Teaching Machines to Classify from Natural Language Interactions

Descriptive Note:

[Technical Report, Doctoral Thesis]

Corporate Author:

Carnegie Mellon University

Personal Author(s):

• Srivastava, Shashank

Report Date:

2018-09-01

Pagination or Media Count:

160

Abstract:

Humans routinely learn new concepts using natural language communications, even in scenarios with limited or no labeled examples. For example, a human can learn the concept of a phishing email from natural language explanations such as phishing emails often request your bank account number. On the other hand, purely inductive learning systems typically require a large collection of labeled data for learning such a concept. We believe that advances in Computational Linguistics and the growing ubiquity of computing devices together can enable people to teach computers classification tasks using natural language interactions.

Descriptors:

• computational science
• ontologies
• computer languages
• automata theory
• natural language processing
• artificial intelligence software
• bayesian networks
• machine learning
• supervised machine learning
• neural networks
• artificial intelligence
• computer programming
• computers
• information systems
• information science
• language
• computational linguistics

Subject Categories:

• Linguistics

Distribution Statement:

[A, Approved For Public Release]