Lightly-supervised Representation Learning with Global Interpretability

Andrew Zupon, Maria Alexeeva, Marco Valenzuela-Escárcega, Ajay Nagesh, Mihai Surdeanu


Abstract
We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-the-art bootstrapping approaches on two datasets: CoNLL-2003 and OntoNotes. Additionally, using these embeddings, our approach outputs a globally-interpretable model consisting of a decision list, by ranking patterns based on their proximity to the average entity embedding in a given class. We show that this interpretable model performs close to our complete bootstrapping model, proving that representation learning can be used to produce interpretable models with small loss in performance. This decision list can be edited by human experts to mitigate some of that loss and in some cases outperform the original model.
Anthology ID:
W19-1504
Volume:
Proceedings of the Third Workshop on Structured Prediction for NLP
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Andre Martins, Andreas Vlachos, Zornitsa Kozareva, Sujith Ravi, Gerasimos Lampouras, Vlad Niculae, Julia Kreutzer
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18–28
Language:
URL:
https://aclanthology.org/W19-1504
DOI:
10.18653/v1/W19-1504
Bibkey:
Cite (ACL):
Andrew Zupon, Maria Alexeeva, Marco Valenzuela-Escárcega, Ajay Nagesh, and Mihai Surdeanu. 2019. Lightly-supervised Representation Learning with Global Interpretability. In Proceedings of the Third Workshop on Structured Prediction for NLP, pages 18–28, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Lightly-supervised Representation Learning with Global Interpretability (Zupon et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/W19-1504.pdf
Data
CoNLL 2003OntoNotes 5.0