Modeling the partial productivity of constructions

Libby Barak, Adele E. Goldberg

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

Abstract

People regularly produce novel sentences that sound nativelike (e.g., she googled us the information), while they also recognize that other novel sentences sound odd, even though they are interpretable (e.g., ? She explained us the information). This work offers a Bayesian, incremental model that learns clusters that correspond to grammatical constructions of different type and token frequencies. Without specifying in advance the number of constructions, their semantic contributions, nor whether any two constructions compete with one another, the model successfully generalizes when appropriate while identifying and suggesting an alternative when faced with overgeneralization errors. Results are consistent with recent psycholinguistic work that demonstrates that the existence of competing alternatives and the frequencies of those alternatives play a key role in the partial productivity of grammatical constructions. The model also goes beyond the psycholinguistic work in that it investigates a role for constructions' overall frequency.

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
Pages131-138
Number of pages8
ISBN (Electronic)9781577357797
StatePublished - Jan 1 2017
Event2017 AAAI Spring Symposium - Stanford, United States
Duration: Mar 27 2017Mar 29 2017

Publication series

NameAAAI Spring Symposium - Technical Report
VolumeSS-17-01 - SS-17-08

Other

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

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Modeling the partial productivity of constructions'. Together they form a unique fingerprint.

  • Cite this

    Barak, L., & Goldberg, A. E. (2017). Modeling the partial productivity of constructions. 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 (pp. 131-138). (AAAI Spring Symposium - Technical Report; Vol. SS-17-01 - SS-17-08). AI Access Foundation.