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

Clifton J. McFate; Kenneth D Forbus

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

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	SS-17-01
Subtitle of host publication	Artificial 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
Publisher	AI Access Foundation
Pages	230-237
Number of pages	8
Volume	SS-17-01 - SS-17-08
ISBN (Electronic)	9781577357797
State	Published - Jan 1 2017
Event	2017 AAAI Spring Symposium - Stanford, United States Duration: Mar 27 2017 → Mar 29 2017

Other

Other	2017 AAAI Spring Symposium
Country	United States
City	Stanford
Period	3/27/17 → 3/29/17

ASJC Scopus subject areas

Artificial Intelligence

Cite this

McFate, C. J., & Forbus, K. D. (2017). A proposal for incorporating analogically learned construction in a feature based parsing framework. In SS-17-01: Artificial 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 (Vol. SS-17-01 - SS-17-08, pp. 230-237). AI Access Foundation.

McFate, Clifton J. ; Forbus, Kenneth D. / A proposal for incorporating analogically learned construction in a feature based parsing framework. SS-17-01: Artificial 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. Vol. SS-17-01 - SS-17-08 AI Access Foundation, 2017. pp. 230-237

@inproceedings{b383527867d844f59571b6913edbe9a8,

title = "A proposal for incorporating analogically learned construction in a feature based parsing framework",

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.",

author = "McFate, {Clifton J.} and Forbus, {Kenneth D}",

year = "2017",

month = jan,

day = "1",

language = "English (US)",

volume = "SS-17-01 - SS-17-08",

pages = "230--237",

booktitle = "SS-17-01",

publisher = "AI Access Foundation",

note = "2017 AAAI Spring Symposium ; Conference date: 27-03-2017 Through 29-03-2017",

}

McFate, CJ & Forbus, KD 2017, A proposal for incorporating analogically learned construction in a feature based parsing framework. in SS-17-01: Artificial 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. vol. SS-17-01 - SS-17-08, AI Access Foundation, pp. 230-237, 2017 AAAI Spring Symposium, Stanford, United States, 3/27/17.

A proposal for incorporating analogically learned construction in a feature based parsing framework. / McFate, Clifton J.; Forbus, Kenneth D.

SS-17-01: Artificial 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. Vol. SS-17-01 - SS-17-08 AI Access Foundation, 2017. p. 230-237.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A proposal for incorporating analogically learned construction in a feature based parsing framework

AU - McFate, Clifton J.

AU - Forbus, Kenneth D

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85028711054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028711054&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85028711054

VL - SS-17-01 - SS-17-08

SP - 230

EP - 237

BT - SS-17-01

PB - AI Access Foundation

T2 - 2017 AAAI Spring Symposium

Y2 - 27 March 2017 through 29 March 2017

ER -

McFate CJ, Forbus KD. A proposal for incorporating analogically learned construction in a feature based parsing framework. In SS-17-01: Artificial 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. Vol. SS-17-01 - SS-17-08. AI Access Foundation. 2017. p. 230-237