A proposal for incorporating analogically learned construction in a feature based parsing framework

Clifton J. McFate, Kenneth D Forbus

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Structure mapping theory is a computational model of analogy that has recently been used to learn FrameNet constructions from a small corpus of annotated text. This paper proposes an approach that uses constructions learned in this way to bootstrap the performance of an existing natural language understanding system with a more traditional feature-based chart parser, EA NLU. We examine the benefits of analogically learned constructions as well as the challenges involved in applying these generalizations to novel text.

Original languageEnglish (US)
Title of host publicationSS-17-01
Subtitle of host publicationArtificial Intelligene for the Social Good; SS-17-02: Computational Construction Grammar and Natural Language Understanding; SS-17-03: Computational Context: Why It's Important, What It Means, and Can It Be Computed?; SS-17-04: Designing the User Experience of Machine Learning Systems; SS-17-05: Interactive Multisensory Object Perception for Embodied Agents; SS-17-06: Learning from Observation of Humans; SS-17-07: Science of Intelligence: Computational Principles of Natural and Artificial Intelligence; SS-17-08: Wellbeing AI: From Machine Learning to Subjectivity Oriented Computing
PublisherAI Access Foundation
Pages230-237
Number of pages8
VolumeSS-17-01 - SS-17-08
ISBN (Electronic)9781577357797
StatePublished - Jan 1 2017
Event2017 AAAI Spring Symposium - Stanford, United States
Duration: Mar 27 2017Mar 29 2017

Other

Other2017 AAAI Spring Symposium
CountryUnited States
CityStanford
Period3/27/173/29/17

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this