@inproceedings{43b6040648024f16a8fb4112ce8b580a,
title = "Building a hebrew semantic role labeling lexical resource from parallel movie subtitles",
abstract = "We present a semantic role labeling resource for Hebrew built semi-automatically through annotation projection from English. This corpus is derived from the multilingual OpenSubtitles dataset and includes short informal sentences, for which reliable linguistic annotations have been computed. We provide a fully annotated version of the data including morphological analysis, dependency syntax and semantic role labeling in both FrameNet and PropBank styles. Sentences are aligned between English and Hebrew, both sides include full annotations and the explicit mapping from the English arguments to the Hebrew ones. We train a neural SRL model on this Hebrew resource exploiting the pre-trained multilingual BERT transformer model, and provide the first available baseline model for Hebrew SRL as a reference point. The code we provide is generic and can be adapted to other languages to bootstrap SRL resources.",
keywords = "Cross-lingual Linguistic Annotations, FrameNet, Hebrew, PropBank, SRL",
author = "Ben Eyal and Michael Elhadad",
note = "Funding Information: This research was supported by the Lynn and William Frankel Center for Computer Science at Ben Gurion University. Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC; 12th International Conference on Language Resources and Evaluation, LREC 2020 ; Conference date: 11-05-2020 Through 16-05-2020",
year = "2020",
month = jan,
day = "1",
language = "English",
series = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "5934--5942",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis",
booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
}