WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing

Cezar Sas, Meriem Beloucif, Anders Søgaard


Abstract
Frame-semantic annotations exist for a tiny fraction of the world’s languages, Wikidata, however, links knowledge base triples to texts in many languages, providing a common, distant supervision signal for semantic parsers. We present WikiBank, a multilingual resource of partial semantic structures that can be used to extend pre-existing resources rather than creating new man-made resources from scratch. We also integrate this form of supervision into an off-the-shelf frame-semantic parser and allow cross-lingual transfer. Using Google’s Sling architecture, we show significant improvements on the English and Spanish CoNLL 2009 datasets, whether training on the full available datasets or small subsamples thereof.
Anthology ID:
2020.lrec-1.515
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
4183–4189
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.515
DOI:
Bibkey:
Cite (ACL):
Cezar Sas, Meriem Beloucif, and Anders Søgaard. 2020. WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4183–4189, Marseille, France. European Language Resources Association.
Cite (Informal):
WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing (Sas et al., LREC 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2020.lrec-1.515.pdf