Uncovering Probabilistic Implications in Typological Knowledge Bases

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Standard

Uncovering Probabilistic Implications in Typological Knowledge Bases. / Bjerva, Johannes; Kementchedjhieva, Yova Radoslavova; Cotterell, Ryan ; Augenstein, Isabelle.

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2019. p. 3924–3930.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Bjerva, J, Kementchedjhieva, YR, Cotterell, R & Augenstein, I 2019, Uncovering Probabilistic Implications in Typological Knowledge Bases. in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pp. 3924–3930, 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 01/07/2019. https://doi.org/10.18653/v1/P19-1382

APA

Bjerva, J., Kementchedjhieva, Y. R., Cotterell, R., & Augenstein, I. (2019). Uncovering Probabilistic Implications in Typological Knowledge Bases. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 3924–3930). Association for Computational Linguistics. https://doi.org/10.18653/v1/P19-1382

Vancouver

Bjerva J, Kementchedjhieva YR, Cotterell R, Augenstein I. Uncovering Probabilistic Implications in Typological Knowledge Bases. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. 2019. p. 3924–3930 https://doi.org/10.18653/v1/P19-1382

Author

Bjerva, Johannes ; Kementchedjhieva, Yova Radoslavova ; Cotterell, Ryan ; Augenstein, Isabelle. / Uncovering Probabilistic Implications in Typological Knowledge Bases. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2019. pp. 3924–3930

Bibtex

@inproceedings{80905706a70544ea8ee18fc3d138b403,
title = "Uncovering Probabilistic Implications in Typological Knowledge Bases",
abstract = "The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have postpositions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which potentially leaves key linguistic universals unexplored. In this paper, we present a computational model which successfully identifies known universals, including Greenberg universals, but also uncovers new ones, worthy of further linguistic investigation. Our approach outperforms baselines previously used for this problem, as well as a strong baseline from knowledge base population.",
author = "Johannes Bjerva and Kementchedjhieva, {Yova Radoslavova} and Ryan Cotterell and Isabelle Augenstein",
year = "2019",
doi = "10.18653/v1/P19-1382",
language = "English",
pages = "3924–3930",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics",
note = "57th Annual Meeting of the Association for Computational Linguistics ; Conference date: 01-07-2019 Through 01-07-2019",

}

RIS

TY - GEN

T1 - Uncovering Probabilistic Implications in Typological Knowledge Bases

AU - Bjerva, Johannes

AU - Kementchedjhieva, Yova Radoslavova

AU - Cotterell, Ryan

AU - Augenstein, Isabelle

PY - 2019

Y1 - 2019

N2 - The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have postpositions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which potentially leaves key linguistic universals unexplored. In this paper, we present a computational model which successfully identifies known universals, including Greenberg universals, but also uncovers new ones, worthy of further linguistic investigation. Our approach outperforms baselines previously used for this problem, as well as a strong baseline from knowledge base population.

AB - The study of linguistic typology is rooted in the implications we find between linguistic features, such as the fact that languages with object-verb word ordering tend to have postpositions. Uncovering such implications typically amounts to time-consuming manual processing by trained and experienced linguists, which potentially leaves key linguistic universals unexplored. In this paper, we present a computational model which successfully identifies known universals, including Greenberg universals, but also uncovers new ones, worthy of further linguistic investigation. Our approach outperforms baselines previously used for this problem, as well as a strong baseline from knowledge base population.

U2 - 10.18653/v1/P19-1382

DO - 10.18653/v1/P19-1382

M3 - Article in proceedings

SP - 3924

EP - 3930

BT - Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 57th Annual Meeting of the Association for Computational Linguistics

Y2 - 1 July 2019 through 1 July 2019

ER -

ID: 239205117