Combining ELECTRA and Adaptive Graph Encoding for Frame Identification

Fabio Tamburini


Abstract
This paper presents contributions in two directions: first we propose a new system for Frame Identification (FI), based on pre-trained text encoders trained discriminatively and graphs embedding, producing state of the art performance and, second, we take in consideration all the extremely different procedures used to evaluate systems for this task performing a complete evaluation over two benchmarks and all possible splits and cleaning procedures used in the FI literature.
Anthology ID:
2022.lrec-1.178
Volume:
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1671–1679
Language:
URL:
https://aclanthology.org/2022.lrec-1.178
DOI:
Bibkey:
Cite (ACL):
Fabio Tamburini. 2022. Combining ELECTRA and Adaptive Graph Encoding for Frame Identification. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1671–1679, Marseille, France. European Language Resources Association.
Cite (Informal):
Combining ELECTRA and Adaptive Graph Encoding for Frame Identification (Tamburini, LREC 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.lrec-1.178.pdf
Code
 ftamburin/electra-age_fe