Abstract
Emotion Classification is the task of automatically associating a text with a human emotion. State-of-the-art models are usually learned using annotated corpora or rely on hand-crafted affective lexicons. We present an emotion classification model that does not require a large annotated corpus to be competitive. We experiment with pretrained language models in both a zero-shot and few-shot configuration. We build several of such models and consider them as biased, noisy annotators, whose individual performance is poor. We aggregate the predictions of these models using a Bayesian method originally developed for modelling crowdsourced annotations. Next, we show that the resulting system performs better than the strongest individual model. Finally, we show that when trained on few labelled data, our systems outperform fully-supervised models.- Anthology ID:
- 2021.ranlp-1.16
- Volume:
- Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
- Month:
- September
- Year:
- 2021
- Address:
- Held Online
- Editors:
- Ruslan Mitkov, Galia Angelova
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 128–137
- Language:
- URL:
- https://aclanthology.org/2021.ranlp-1.16
- DOI:
- Cite (ACL):
- Angelo Basile, Guillermo Pérez-Torró, and Marc Franco-Salvador. 2021. Probabilistic Ensembles of Zero- and Few-Shot Learning Models for Emotion Classification. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 128–137, Held Online. INCOMA Ltd..
- Cite (Informal):
- Probabilistic Ensembles of Zero- and Few-Shot Learning Models for Emotion Classification (Basile et al., RANLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.ranlp-1.16.pdf
- Data
- DailyDialog, MultiNLI, XNLI