KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations

Fabio Massimo Zanzotto, Andrea Santilli, Leonardo Ranaldi, Dario Onorati, Pierfrancesco Tommasino, Francesca Fallucchi


Abstract
Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality in downstream tasks due to the success of large-scale textual representation learners. In this paper, we propose KERMIT (Kernel-inspired Encoder with Recursive Mechanism for Interpretable Trees) to embed symbolic syntactic parse trees into artificial neural networks and to visualize how syntax is used in inference. We experimented with KERMIT paired with two state-of-the-art transformer-based universal sentence encoders (BERT and XLNet) and we showed that KERMIT can indeed boost their performance by effectively embedding human-coded universal syntactic representations in neural networks
Anthology ID:
2020.emnlp-main.18
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:
256–267
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.18
DOI:
10.18653/v1/2020.emnlp-main.18
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.18.pdf