Beck, Tilman ; Waldis, Andreas ; Gurevych, Iryna (2023)
Robust Integration of Contextual Information for Cross-Target Stance Detection.
12th Joint Conference on Lexical and Computational Semantics. Toronto, Canada (13.-14.07.2023)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Stance detection deals with identifying an author’s stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information which allows for inferring the stance correctly.Complementary context can be found in knowledge bases but integrating the context into pretrained language models is non-trivial due to the graph structure of standard knowledge bases. To overcome this, we explore an approach to integrate contextual information as text which allows for integrating contextual information from heterogeneous sources, such as structured knowledge sources and by prompting large language models. Our approach can outperform competitive baselines on a large and diverse stance detection benchmark in a cross-target setup, i.e. for targets unseen during training. We demonstrate that it is more robust to noisy context and can regularize for unwanted correlations between labels and target-specific vocabulary. Finally, it is independent of the pretrained language model in use.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2023 |
| Autor(en): | Beck, Tilman ; Waldis, Andreas ; Gurevych, Iryna |
| Art des Eintrags: | Bibliographie |
| Titel: | Robust Integration of Contextual Information for Cross-Target Stance Detection |
| Sprache: | Englisch |
| Publikationsjahr: | 11 Juli 2023 |
| Verlag: | ACL |
| Buchtitel: | StarSEM 2023: The 12th Joint Conference on Lexical and Computational Semantics - Proceedings of the Conference (*SEM 2023) |
| Veranstaltungstitel: | 12th Joint Conference on Lexical and Computational Semantics |
| Veranstaltungsort: | Toronto, Canada |
| Veranstaltungsdatum: | 13.-14.07.2023 |
| URL / URN: | https://aclanthology.org/2023.starsem-1.43/ |
| Kurzbeschreibung (Abstract): | Stance detection deals with identifying an author’s stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual information which allows for inferring the stance correctly.Complementary context can be found in knowledge bases but integrating the context into pretrained language models is non-trivial due to the graph structure of standard knowledge bases. To overcome this, we explore an approach to integrate contextual information as text which allows for integrating contextual information from heterogeneous sources, such as structured knowledge sources and by prompting large language models. Our approach can outperform competitive baselines on a large and diverse stance detection benchmark in a cross-target setup, i.e. for targets unseen during training. We demonstrate that it is more robust to noisy context and can regularize for unwanted correlations between labels and target-specific vocabulary. Finally, it is independent of the pretrained language model in use. |
| Freie Schlagworte: | moveUKP_p_KRITIS,UKP_p_kopocov |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung |
| Hinterlegungsdatum: | 25 Jul 2023 11:44 |
| Letzte Änderung: | 26 Jul 2023 09:49 |
| PPN: | 509927599 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum