PhD Topics

Multilingual Contextualized Processing of Basic Syntactic-semantic Elements

Guidelines

The aim of this proposal is to develop an automatic processing approach for minimal syntactic entities – syntaxemes, which were first described by G.A. Zolotova in the context of her work on the functional principle​ of meaningful language entities [1]. A syntaxeme has a set of functions it can convey in different syntactic contexts. As a concrete example, prepositional phrases and cased nominal phrases are basic units (syntaxemes) with grammatical meaning, which may be partially autonomous and partially dependent on the surrounding syntactic context. Previous work with Zolotova's syntactic dictionary [2] showed that the complex ontology of prepositional syntaxemes and their semantic functions can be condensed into an efficient system of prepositional senses that can be used for automatic semantic classification of prepositional phrases with the help of deep learning.

The proposed research will try to apply the same approach to other syntaxemes, e.g., the morphological case system as described in Zolotova's work. In addition, the system of syntax-semantic interface in cased nominal and prepositional phrases will be tested on other Slavic languages, using the Universal Dependencies data [5]. A cross-linguistically applicable description of prepositional/case meanings will be sought which could improve the current Enhanced Universal Dependencies standard for annotation of oblique nominals, and help natural language understanding systems.

References

[1] Zolotova G.A. (1988). Syntactic dictionary: Repertory of elementary units of Russian Syntax. Moscow: Nauka, 1988. – 440 p.

[2] Gudkov V., Golovina N., Mitrofanova O., Zakharov V. (2019). Russian Prepositional Phrase Semantic Labelling with Word Embedding-based Classifier, R. Piotrowski's Readings in Language Engineering and Applied Linguistics (PRLEAL)

[3] Efremova T.F. Explanatory dictionary of functional parts of speech of the Russian language.

[4] Zolotova G.A. (2006). Communicative aspects of Russian syntax

[5] Nivre J., de Marneffe M.-C., Ginter F., Hajič J., Manning C., Pyysalo S., Schuster S., Tyers F., Zeman D. (2020). Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection. In: Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020), pp. 4027-4036, European Language Resources Association, Marseille, France, ISBN 979-10-95546-34-4

[6] Kondratyuk D., Straka M. (2019). 75 Languages, 1 Model: Parsing Universal Dependencies Universally, EMNLP-IJCNLP

[7] Chi, Ethan & Hewitt, John & Manning, Christopher. (2020). Finding Universal Grammatical Relations in Multilingual BERT, ACL