Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora

Publikation

Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora

Plaza-del-Arco, Flor Miriam; Martín-Valdivia, María-Teresa; Klinger, Roman (2022): Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora, in: Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, u. a. (Hrsg.), Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju: International Committee on Computational Linguistics, S. 6805–6817.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Plaza-del-Arco, Flor Miriam
Martín-Valdivia, María-Teresa
Titel des Sammelwerks
Proceedings of the 29th International Conference on Computational Linguistics
Herausgeberin(nen)/Herausgeber des Sammelwerks
Calzolari, Nicoletta; Huang, Chu-Ren; Kim, Hansaem; Pustejovsky, James; Wanner, Leo; Choi, Key-Sun; Ryu, Pum-Mo; Chen, Hsin-Hsi; Donatelli, Lucia; Ji, Heng; Kurohashi, Sadao; Paggio, Patrizia; Xue, Nianwen; Kim, Seokhwan; Hahm, Younggyun; He, Zhong; Kyungil Lee, Tony; Santus, Enrico; Bond, Francis; Na, Seung-Hoon
Konferenz
29th International Conference on Computational Linguistics (COLING), Oktober 2022, Gyeongju
Verlagsangabe
International Committee on Computational Linguistics : Gyeongju
Erscheinungsjahr
2022
Sprache(n)
Englisch
URL
Abstract

Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in which the labels need to be predefined. A solution to obtain a model with a flexible set of labels is to use the paradigm of zero-shot learning as a natural language inference task, which in addition adds the advantage of not needing any labeled training data. This raises the question how to prompt a natural language inference model for zero-shot learning emotion classification. Options for prompt formulations include the emotion name anger alone or the statement “This text expresses anger”. With this paper, we analyze how sensitive a natural language inference-based zero-shot-learning classifier is to such changes to the prompt under consideration of the corpus: How carefully does the prompt need to be selected? We perform experiments on an established set of emotion datasets presenting different language registers according to different sources (tweets, events, blogs) with three natural language inference models and show that indeed the choice of a particular prompt formulation needs to fit to the corpus. We show that this challenge can be tackled with combinations of multiple prompts. Such ensemble is more robust across corpora than individual prompts and shows nearly the same performance as the individual best prompt for a particular corpus.

GND-Schlagwort(e)
Computerlinguistik
Maschinelle Sprachverarbeitung
Inferenz <Künstliche Intelligenz>
Gefühl
Freie Schlagwort(e)
Natural Language Inference Prompts
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
ST 306
Peer Reviewed
ja
Internationale Verbreitung
ja
Open-Access-Zeitschrift
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
07.03.2024
Projekt(e)

Permalink: https://fis.uni-bamberg.de/handle/uniba/93883 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 16.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.