What's wrong with Hebrew nlp? And how to make it right

Reut Tsarfaty, Amit Seker, Shoval Sadde, Stav Klein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

For languages with simple morphology, such as English, automatic annotation pipelines such as spaCy or Stanford's CoreNLP successfully serve AI/DS projects in academia and the industry. For many morphologically-rich languages (MRLs), similar pipelines show suboptimal performance that limits their applicability for text analysis in research and commerical use. The suboptimal performance is mainly due to errors in early morphological disambiguation decisions, which cannot be recovered later in the pipeline, yielding incoherent annotations on the whole. In this paper we describe the design and use of the ONLP suite, a joint morpho-syntactic parsing framework for processing Modern Hebrew texts. The joint inference over morphology and syntax substantially limits error propagation, and leads to high accuracy. ONLP provides rich and expressive output which already serves diverse academic and commercial needs. Its accompanying demo further serves educational activities, introducing Hebrew NLP intricacies to researchers and non-researchers alike.

Original languageEnglish
Title of host publicationEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Proceedings of System Demonstrations
PublisherAssociation for Computational Linguistics (ACL)
Pages259-264
Number of pages6
ISBN (Electronic)9781950737925
StatePublished - 2019
Externally publishedYes
Event2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, China
Duration: 3 Nov 20197 Nov 2019

Publication series

NameEMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Proceedings of System Demonstrations

Conference

Conference2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Country/TerritoryChina
CityHong Kong
Period3/11/197/11/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics.

Funding

We thank the NLPH community, in particular Shay Palachi, Amit Shkolnick and Yuval Feinstein, for discussion and insightful comments. We further thank Avi Bivas (Israel Innovation Authority) and Milo Avisar for promoting NLP initiatives in Israel. This research is supported by an ISF grant (1739/26) and an ERC Starting grant (677352), for which we are grateful.

FundersFunder number
Israel Innovation Authority
European Research Council677352
Israel Science Foundation1739/26

    Fingerprint

    Dive into the research topics of 'What's wrong with Hebrew nlp? And how to make it right'. Together they form a unique fingerprint.

    Cite this