Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change

Haim Dubossarsky, Simon Hengchen, Nina Tahmasebi, Dominik Schlechtweg

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Kuvaus

State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.
Alkuperäiskielienglanti
OtsikkoThe 57th Annual Meeting of the Association for Computational Linguistics (ACL2019) : Proceedings of the Conference
ToimittajatAnna Korhonen, David Traum, Lluís Màrquez
Sivumäärä14
JulkaisupaikkaStroudsburg
KustantajaACL
Julkaisupäiväheinäkuuta 2019
Sivut457-470
ISBN (elektroninen)978-1-950737-48-2
TilaJulkaistu - heinäkuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaAnnual Meeting of the Association for Computational Linguistics - Florence, Italia
Kesto: 28 heinäkuuta 20192 elokuuta 2019
Konferenssinumero: 57
http://www.acl2019.org/EN/index.xhtml

Lisätietoja

Code produced for this paper is available at: https://github.com/Garrafao/TemporalReferencing

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet
  • 6121 Kielitieteet

Lainaa tätä

Dubossarsky, H., Hengchen, S., Tahmasebi, N., & Schlechtweg, D. (2019). Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. teoksessa A. Korhonen, D. Traum, & L. Màrquez (Toimittajat), The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019): Proceedings of the Conference (Sivut 457-470). Stroudsburg: ACL.
Dubossarsky, Haim ; Hengchen, Simon ; Tahmasebi, Nina ; Schlechtweg, Dominik. / Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019): Proceedings of the Conference. Toimittaja / Anna Korhonen ; David Traum ; Lluís Màrquez . Stroudsburg : ACL, 2019. Sivut 457-470
@inproceedings{50ad383b55c54e6e90fb1841f6413480,
title = "Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change",
abstract = "State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.",
keywords = "113 Computer and information sciences, Natural language processing, Computational linguistics, 6121 Languages",
author = "Haim Dubossarsky and Simon Hengchen and Nina Tahmasebi and Dominik Schlechtweg",
note = "Code produced for this paper is available at: https://github.com/Garrafao/TemporalReferencing",
year = "2019",
month = "7",
language = "English",
pages = "457--470",
editor = "Anna Korhonen and Traum, {David } and {M{\`a}rquez }, {Llu{\'i}s }",
booktitle = "The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019)",
publisher = "ACL",
address = "United States",

}

Dubossarsky, H, Hengchen, S, Tahmasebi, N & Schlechtweg, D 2019, Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. julkaisussa A Korhonen, D Traum & L Màrquez (toim), The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019): Proceedings of the Conference. ACL, Stroudsburg, Sivut 457-470, Annual Meeting of the Association for Computational Linguistics, Florence, Italia, 28/07/2019.

Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. / Dubossarsky, Haim; Hengchen, Simon; Tahmasebi, Nina; Schlechtweg, Dominik.

The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019): Proceedings of the Conference. toim. / Anna Korhonen; David Traum; Lluís Màrquez . Stroudsburg : ACL, 2019. s. 457-470.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

TY - GEN

T1 - Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change

AU - Dubossarsky, Haim

AU - Hengchen, Simon

AU - Tahmasebi, Nina

AU - Schlechtweg, Dominik

N1 - Code produced for this paper is available at: https://github.com/Garrafao/TemporalReferencing

PY - 2019/7

Y1 - 2019/7

N2 - State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.

AB - State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding alignment, it is less affected by this noise. We show that, trained on a diachronic corpus, the skip-gram with negative sampling architecture with temporal referencing outperforms alignment models on a synthetic task as well as a manual testset. We introduce a principled way to simulate lexical semantic change and systematically control for possible biases.

KW - 113 Computer and information sciences

KW - Natural language processing

KW - Computational linguistics

KW - 6121 Languages

M3 - Conference contribution

SP - 457

EP - 470

BT - The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019)

A2 - Korhonen, Anna

A2 - Traum, David

A2 - Màrquez , Lluís

PB - ACL

CY - Stroudsburg

ER -

Dubossarsky H, Hengchen S, Tahmasebi N, Schlechtweg D. Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change. julkaisussa Korhonen A, Traum D, Màrquez L, toimittajat, The 57th Annual Meeting of the Association for Computational Linguistics (ACL2019): Proceedings of the Conference. Stroudsburg: ACL. 2019. s. 457-470