Nothing Special   »   [go: up one dir, main page]

Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains

Eyal Shnarch, Leshem Choshen, Guy Moshkowich, Ranit Aharonov, Noam Slonim


Abstract
Approaching new data can be quite deterrent; you do not know how your categories of interest are realized in it, commonly, there is no labeled data at hand, and the performance of domain adaptation methods is unsatisfactory. Aiming to assist domain experts in their first steps into a new task over a new corpus, we present an unsupervised approach to reveal complex rules which cluster the unexplored corpus by its prominent categories (or facets). These rules are human-readable, thus providing an important ingredient which has become in short supply lately - explainability. Each rule provides an explanation for the commonality of all the texts it clusters together. The experts can then identify which rules best capture texts of their categories of interest, and utilize them to deepen their understanding of these categories. These rules can also bootstrap the process of data labeling by pointing at a subset of the corpus which is enriched with texts demonstrating the target categories. We present an extensive evaluation of the usefulness of these rules in identifying target categories, as well as a user study which assesses their interpretability.
Anthology ID:
2020.findings-emnlp.243
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2678–2697
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.243
DOI:
10.18653/v1/2020.findings-emnlp.243
Bibkey:
Cite (ACL):
Eyal Shnarch, Leshem Choshen, Guy Moshkowich, Ranit Aharonov, and Noam Slonim. 2020. Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2678–2697, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains (Shnarch et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.243.pdf
Optional supplementary material:
 2020.findings-emnlp.243.OptionalSupplementaryMaterial.txt
Data
Terms of Service