Creating Linked Data Morphological Language Resources with MMoOn - The Hebrew Morpheme Inventory

What it is about

The authors build a Linked Data (RDF) model for morphemes, the Multilingual Morpheme Ontology (MMoOn), and fill it with a Hebrew inventory. The source is a hand-made vocabulary table of about 52,000 entries; after syntactic cleaning, about 11,600 carry morphological information. Hebrew roots (1,795 in total) and transfix patterns are kept as separate resources, so a word-form is a root combined with a pattern. Verb forms for the first seven Barkali binyan groups are generated from roots by script, giving 98,824 word-forms for 1,568 lexemes. The paper reports the size of the result and the 1,848 links to BabelNet lexical entries; it gives no evaluation of the generated forms.

Ideas

• I1. Keep root, transfix pattern and word-form as separate tables in the Torah dictionary. macula dict has lemmas and Strong's numbers but no roots yet; a root column would make the lemma-to-root lookup deterministic.
• I2. Generate candidate verb forms from a root and a binyan table, then measure how many of them occur in the MACULA text. This is a measure of coverage, which the paper does not give.
• I3. The cleaning rules (drop rows with invalid syntax, several entries in one column, or no word class) are a validator for any lexicon import Mova makes, such as the Wiktionary-derived tables.

For Mova

I1 goes into tools/macula (dictionary) and The lexicon. I2 is a test for The verb (weak and strong binyan paradigms). I3 is a check in the tools/wikt-* import. The licence is NC: the inventory is for reading and measurement only, and nothing from it is built into a release.

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{klimek2016creating,
  title = {{Creating Linked Data Morphological Language Resources with MMoOn - The Hebrew Morpheme Inventory}},
  author = {Klimek, Bettina and Arndt, Natanael and Krause, Sebastian and Arndt, Timotheus},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  url = {https://aclanthology.org/L16-1143/}
}

References

19 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Barkali, S. (1962). Luax HaP’alim HaShalem (the complete verbs table). Reuven Mass, Jerusalem. In Hebrew. find
2. Beermann, D. and Mihaylov, P. (2014). Typecraft collaborative databasing and resource sharing for linguists. Language Resources and Evaluation, 48(2). find
3. Berners-Lee, T. (2009). Linked Data. Design issues, W3C, June. http://www.w3.org/DesignIssues/Linked Data.html. ↗
4. Chiarcos, C., Hellmann, S., and Nordhoff, S. (2012). Linked Data in Linguistics. Representing Language Data and Metadata. Springer. find
5. Chiarcos, C. (2008). An ontology of linguistic annotations. LDV Forum, pages 1–136. find
6. Cimiano, P., McCrae, J., Buitelaar, P., and Stintek, M. (2011). Lexinfo: A declarative model for the lexicon-ontology interface. Web Semantics: Science, Services and Agents on the World Wide Web, pages 29–51. find
7. Creutz, M. and Lagus, K. (2005a). Inducing the morphological lexicon of a natural language from unannotated text. Proceedings of the International and Interdisciplinary Conference on Adaptive Knowledge Representation and Reasoning (AKRR’05), 1:106–113. find
8. Creutz, M. and Lagus, K. (2005b). Unsupervised morpheme segmentation and morphology induction from text corpora using morfessor 1.0. Helsinki University of Technology. find
9. Even-Shoshan, A. e. a. (2003). Even Shoshan Dictionary. Jerusalem: Qiryat-Sefer Publishing.(Hebrew). find
10. Farrar, S. and Langendoen, D. T. (2010). An owl-dl implementation of gold. Linguistic Modeling of Information and Markup Languages, pages 45–66. find
11. Itai, A. and Wintner, S. (2008). Language resources for hebrew. Language Resources and Evaluation, 42(1):75– 98. find
12. Lehmann, C. (2004). Data in linguistics. The Linguistic Review, 21:175–210. find
13. McCarthy, J. J. (1981). A prosodic theory of nonconcatenative morphology. Linguistic inquiry, pages 373–418. find
14. McCrae, J., Spohr, D., and Cimiano, P. (2011). Linking lexical resources and ontologies on the semantic web with lemon. The semantic web: research and applications, pages 245–259. find
15. Navigli, R. and Ponzetto, S. P. (2012). BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artificial Intelligence, 193:217–250. find
16. Sagot, B. (2010). The lefff, a freely available and large-coverage morphological and syntactic lexicon for french. 7th international conference on Language Resources and Evaluation (LREC). find
17. Sérasset, G. (2012). Dbnary: Wiktionary as a lemon-based multilingual lexical resource in rdf. Semantic Web Journal-Special issue on Multilingual Linked Open Data. find
18. Yona, S. and Wintner, S. (2008). A finite-state morphological grammar of hebrew. Natural Language Engineering, 14:173–190, 4. find our card
19. Zielinski, A. and Simon, C. (2009). Morphisto – an open source morphological analyzer for German. Proceedings of the 2009 conference on Finite-State Methods and Natural Language Processing: Post-proceedings of the 7th International Workshop FSMNLP 2008. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2016-klimek-creating-linked-data-morphological-language/