Learned Construction Grammars Converge Across Registers Given Increased Exposure (2021)
This paper measures the impact of increased exposure on whether learned construction grammars converge onto shared representations when trained on data from different registers. Register influences the frequency of constructions, with some structures common in formal but not informal usage. We expect that a grammar induction algorithm exposed to different registers will acquire different constructions. To what degree does increased exposure lead to the convergence of register-specific grammars? The experiments in this paper simulate language learning in 12 languages (half Germanic and half Romance) with corpora representing three registers (Twitter, Wikipedia, Web). These simulations are repeated with increasing amounts of exposure, from 100k to 2 million words, to measure the impact of exposure on the convergence of grammars. The results show that increased exposure does lead to converging grammars across all languages. In addition, a shared core of register-universal constructions remains constant across increasing amounts of exposure.
CitationDunn J, Tayyar Madabushi H (2021). Learned Construction Grammars Converge Across Registers Given Increased Exposure. Conference on Natural Language Learning (CoNLL). Proceedings of the Conference on Natural Language Learning.
This citation is automatically generated and may be unreliable. Use as a guide only.
ANZSRC Fields of Research47 - Language, communication and culture::4704 - Linguistics::470403 - Computational linguistics
47 - Language, communication and culture::4704 - Linguistics::470409 - Linguistic structures (incl. phonology, morphology and syntax)
47 - Language, communication and culture::4704 - Linguistics::470404 - Corpus linguistics
47 - Language, communication and culture::4704 - Linguistics::470401 - Applied linguistics and educational linguistics
47 - Language, communication and culture::4703 - Language studies::470304 - Comparative language studies
RightsAll rights reserved unless otherwise stated
Showing items related by title, author, creator and subject.
Nini A; Dunn, Jonathan (Association for Computational Linguistics, 2021)This paper asks whether a distinction between production-based and perception-based grammar induction influences either (i) the growth curve of grammars and lexicons or (ii) the similarity between representations learned ...
Dunn J (2018)This paper formulates and evaluates a series of multi-unit measures of directional association, building on the pairwise ΔP measure, that are able to quantify association in sequences of varying length and type ...
Dunn J (Walter de Gruyter GmbH, 2013)This paper argues that two properties of the linguistic structure of an utterance influence and partially determine whether the utterance has a metaphoric meaning that results in a stable interpretation: (i) degree of ...