Dissecting Span Identification Tasks with Performance Prediction

Sean Papay, Roman Klinger, Sebastian Padó


Abstract
Span identification (in short, span ID) tasks such as chunking, NER, or code-switching detection, ask models to identify and classify relevant spans in a text. Despite being a staple of NLP, and sharing a common structure, there is little insight on how these tasks’ properties influence their difficulty, and thus little guidance on what model families work well on span ID tasks, and why. We analyze span ID tasks via performance prediction, estimating how well neural architectures do on different tasks. Our contributions are: (a) we identify key properties of span ID tasks that can inform performance prediction; (b) we carry out a large-scale experiment on English data, building a model to predict performance for unseen span ID tasks that can support architecture choices; (c), we investigate the parameters of the meta model, yielding new insights on how model and task properties interact to affect span ID performance. We find, e.g., that span frequency is especially important for LSTMs, and that CRFs help when spans are infrequent and boundaries non-distinctive.
Anthology ID:
2020.emnlp-main.396
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4881–4895
Language:
URL:
https://aclanthology.org/2020.emnlp-main.396
DOI:
10.18653/v1/2020.emnlp-main.396
Bibkey:
Cite (ACL):
Sean Papay, Roman Klinger, and Sebastian Padó. 2020. Dissecting Span Identification Tasks with Performance Prediction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4881–4895, Online. Association for Computational Linguistics.
Cite (Informal):
Dissecting Span Identification Tasks with Performance Prediction (Papay et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.396.pdf
Video:
 https://slideslive.com/38939121