Abstract
Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect – of vital practical importance – has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder’s output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach – which leverages statistics from top-k predictions by a beam search – significantly reduces calibration errors of the predictions of a generative sequence labeling model.- Anthology ID:
- 2024.uncertainlp-1.6
- Volume:
- Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)
- Month:
- March
- Year:
- 2024
- Address:
- St Julians, Malta
- Editors:
- Raúl Vázquez, Hande Celikkanat, Dennis Ulmer, Jörg Tiedemann, Swabha Swayamdipta, Wilker Aziz, Barbara Plank, Joris Baan, Marie-Catherine de Marneffe
- Venues:
- UncertaiNLP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 62–69
- Language:
- URL:
- https://aclanthology.org/2024.uncertainlp-1.6
- DOI:
- Cite (ACL):
- Kazuma Hashimoto, Iftekhar Naim, and Karthik Raman. 2024. How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?. In Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), pages 62–69, St Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling? (Hashimoto et al., UncertaiNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2024.uncertainlp-1.6.pdf