Learned Construction Grammars Converge Across Registers Given Increased Exposure
dc.contributor.author | Tayyar Madabushi H | |
dc.contributor.author | Dunn, Jonathan | |
dc.date.accessioned | 2021-11-07T23:42:03Z | |
dc.date.available | 2021-11-07T23:42:03Z | |
dc.date.issued | 2021 | en |
dc.date.updated | 2021-10-13T07:14:27Z | |
dc.description.abstract | 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. | en |
dc.identifier.citation | Dunn 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. | en |
dc.identifier.uri | https://hdl.handle.net/10092/102887 | |
dc.language.iso | en | |
dc.publisher | Association for Computational Linguistics | en |
dc.rights | All rights reserved unless otherwise stated | en |
dc.rights.uri | http://hdl.handle.net/10092/17651 | en |
dc.subject.anzsrc | Fields of Research::47 - Language, communication and culture::4704 - Linguistics::470403 - Computational linguistics | en |
dc.subject.anzsrc | Fields of Research::47 - Language, communication and culture::4704 - Linguistics::470409 - Linguistic structures (incl. phonology, morphology and syntax) | en |
dc.subject.anzsrc | Fields of Research::47 - Language, communication and culture::4704 - Linguistics::470404 - Corpus linguistics | en |
dc.subject.anzsrc | Fields of Research::47 - Language, communication and culture::4704 - Linguistics::470401 - Applied linguistics and educational linguistics | en |
dc.subject.anzsrc | Fields of Research::47 - Language, communication and culture::4703 - Language studies::470304 - Comparative language studies | en |
dc.title | Learned Construction Grammars Converge Across Registers Given Increased Exposure | en |
dc.type | Conference Contributions - Published | en |
uc.college | Faculty of Arts | |
uc.department | Language, Social and Political Sciences |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- CoNLL_21.pdf
- Size:
- 520.33 KB
- Format:
- Adobe Portable Document Format
- Description:
- Accepted version