Instance-Based Neural Dependency Parsing

Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, Kentaro Inui


Abstract
Abstract Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set. The training edges are explicitly used for the predictions; thus, it is easy to grasp the contribution of each edge to the predictions. Our experiments show that our instance-based models achieve competitive accuracy with standard neural models and have the reasonable plausibility of instance-based explanations.
Anthology ID:
2021.tacl-1.89
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1493–1507
Language:
URL:
https://aclanthology.org/2021.tacl-1.89
DOI:
10.1162/tacl_a_00439
Bibkey:
Cite (ACL):
Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa, and Kentaro Inui. 2021. Instance-Based Neural Dependency Parsing. Transactions of the Association for Computational Linguistics, 9:1493–1507.
Cite (Informal):
Instance-Based Neural Dependency Parsing (Ouchi et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.89.pdf