Switching Contexts: Transportability Measures for NLPCitation formats

Standard

Switching Contexts: Transportability Measures for NLP. / Marshall, Guy; Thayaparan, Mokanarangan; Osborne, Philip; Freitas, Andre.

14th International Conference on Computational Semantics (IWCS 2021) . 2021.

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Harvard

Marshall, G, Thayaparan, M, Osborne, P & Freitas, A 2021, Switching Contexts: Transportability Measures for NLP. in 14th International Conference on Computational Semantics (IWCS 2021) . 14th International Conference on Computational Semantics , Groningen, Netherlands, 16/06/21.

APA

Marshall, G., Thayaparan, M., Osborne, P., & Freitas, A. (Accepted/In press). Switching Contexts: Transportability Measures for NLP. In 14th International Conference on Computational Semantics (IWCS 2021)

Vancouver

Marshall G, Thayaparan M, Osborne P, Freitas A. Switching Contexts: Transportability Measures for NLP. In 14th International Conference on Computational Semantics (IWCS 2021) . 2021

Author

Marshall, Guy ; Thayaparan, Mokanarangan ; Osborne, Philip ; Freitas, Andre. / Switching Contexts: Transportability Measures for NLP. 14th International Conference on Computational Semantics (IWCS 2021) . 2021.

Bibtex

@inproceedings{9516bbd4984f4cbd8e6a073826c2f7a2,
title = "Switching Contexts: Transportability Measures for NLP",
abstract = "This paper explores the topic of transportability, as a sub-area of generalisability. By proposing the utilisation of metrics based on well-established statistics, we are able to estimate the change in performance of NLP models in new contexts. Defining a new measure for transportability may allow for better estimation of NLP system performance in new domains, and is crucial when assessing the performance of NLP systems in new tasks and domains. Through several instances of increasing complexity, we demonstrate how lightweight domain similarity measures can be used as estimators for the transportability in NLP applications. The proposed transportability measures are evaluated in the context of Named Entity Recognition and Natural Language Inference tasks.",
author = "Guy Marshall and Mokanarangan Thayaparan and Philip Osborne and Andre Freitas",
year = "2021",
month = apr,
day = "16",
language = "English",
booktitle = "14th International Conference on Computational Semantics (IWCS 2021)",
note = "14th International Conference on Computational Semantics , IWCS 2021 ; Conference date: 16-06-2021 Through 18-06-2021",

}

RIS

TY - GEN

T1 - Switching Contexts: Transportability Measures for NLP

AU - Marshall, Guy

AU - Thayaparan, Mokanarangan

AU - Osborne, Philip

AU - Freitas, Andre

PY - 2021/4/16

Y1 - 2021/4/16

N2 - This paper explores the topic of transportability, as a sub-area of generalisability. By proposing the utilisation of metrics based on well-established statistics, we are able to estimate the change in performance of NLP models in new contexts. Defining a new measure for transportability may allow for better estimation of NLP system performance in new domains, and is crucial when assessing the performance of NLP systems in new tasks and domains. Through several instances of increasing complexity, we demonstrate how lightweight domain similarity measures can be used as estimators for the transportability in NLP applications. The proposed transportability measures are evaluated in the context of Named Entity Recognition and Natural Language Inference tasks.

AB - This paper explores the topic of transportability, as a sub-area of generalisability. By proposing the utilisation of metrics based on well-established statistics, we are able to estimate the change in performance of NLP models in new contexts. Defining a new measure for transportability may allow for better estimation of NLP system performance in new domains, and is crucial when assessing the performance of NLP systems in new tasks and domains. Through several instances of increasing complexity, we demonstrate how lightweight domain similarity measures can be used as estimators for the transportability in NLP applications. The proposed transportability measures are evaluated in the context of Named Entity Recognition and Natural Language Inference tasks.

M3 - Conference contribution

BT - 14th International Conference on Computational Semantics (IWCS 2021)

T2 - 14th International Conference on Computational Semantics

Y2 - 16 June 2021 through 18 June 2021

ER -