Returning the N to NLP: Towards Contextually Personalized Classification Models
L. Flek. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Seite 7828--7838. Online, Association for Computational Linguistics, (Juli 2020)
DOI: 10.18653/v1/2020.acl-main.700
Zusammenfassung
Most NLP models today treat language as universal, even though socio- and psycholingustic research shows that the communicated message is influenced by the characteristics of the speaker as well as the target audience. This paper surveys the landscape of personalization in natural language processing and related fields, and offers a path forward to mitigate the decades of deviation of the NLP tools from sociolingustic findings, allowing to flexibly process the ``natural'' language of each user rather than enforcing a uniform NLP treatment. It outlines a possible direction to incorporate these aspects into neural NLP models by means of socially contextual personalization, and proposes to shift the focus of our evaluation strategies accordingly.
Beschreibung
Returning the N to NLP: Towards Contextually Personalized Classification Models - ACL Anthology
%0 Conference Paper
%1 flek-2020-returning
%A Flek, Lucie
%B Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%C Online
%D 2020
%I Association for Computational Linguistics
%K antrag deconspire language models nlp personalized social
%P 7828--7838
%R 10.18653/v1/2020.acl-main.700
%T Returning the N to NLP: Towards Contextually Personalized Classification Models
%U https://www.aclweb.org/anthology/2020.acl-main.700
%X Most NLP models today treat language as universal, even though socio- and psycholingustic research shows that the communicated message is influenced by the characteristics of the speaker as well as the target audience. This paper surveys the landscape of personalization in natural language processing and related fields, and offers a path forward to mitigate the decades of deviation of the NLP tools from sociolingustic findings, allowing to flexibly process the ``natural'' language of each user rather than enforcing a uniform NLP treatment. It outlines a possible direction to incorporate these aspects into neural NLP models by means of socially contextual personalization, and proposes to shift the focus of our evaluation strategies accordingly.
@inproceedings{flek-2020-returning,
abstract = {Most NLP models today treat language as universal, even though socio- and psycholingustic research shows that the communicated message is influenced by the characteristics of the speaker as well as the target audience. This paper surveys the landscape of personalization in natural language processing and related fields, and offers a path forward to mitigate the decades of deviation of the NLP tools from sociolingustic findings, allowing to flexibly process the {``}natural{''} language of each user rather than enforcing a uniform NLP treatment. It outlines a possible direction to incorporate these aspects into neural NLP models by means of socially contextual personalization, and proposes to shift the focus of our evaluation strategies accordingly.},
added-at = {2020-09-05T15:53:47.000+0200},
address = {Online},
author = {Flek, Lucie},
biburl = {https://www.bibsonomy.org/bibtex/2ff43653c08c9ec95f55fd4cfd901db6d/schwemmlein},
booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
description = {Returning the N to NLP: Towards Contextually Personalized Classification Models - ACL Anthology},
doi = {10.18653/v1/2020.acl-main.700},
interhash = {81e12f85b9c9964f8e84003e17188d91},
intrahash = {ff43653c08c9ec95f55fd4cfd901db6d},
keywords = {antrag deconspire language models nlp personalized social},
month = jul,
pages = {7828--7838},
publisher = {Association for Computational Linguistics},
timestamp = {2020-09-05T15:53:47.000+0200},
title = {Returning the {N} to {NLP}: {T}owards Contextually Personalized Classification Models},
url = {https://www.aclweb.org/anthology/2020.acl-main.700},
year = 2020
}