Adjunct role labeling for Russian

P. 367–377.

Kazakov R., Lyashevskaya O.

The task of the semantic role labeling usually focuses on identifying and classifying the core, obligatory argu­ ments of the predicate. The adjuncts of Time, Location, etc. (non­core, modifier arguments) are considered on the periphery of the task [30] and even doing the easy part of it [44], despite the fact that they are highly integrated into the clause structure and may non­trivially interact with the meaning of the verb [4, 32]. In this paper, we present experiments on labeling the adjunct roles of LOCATION, TIME, MANNER, DEGREE, REASON, and PURPOSE, based on the manually annotated Adjuncts­FrameBank data set. The results show an average F1­score of 0.94 on the gold adjunct phrase annotations using the word2vec representations of adjuncts, word2vec representations of pre­ dicates, and the moprhosyntactic marking of adjuncts. Our findings generally corroborate the theoretical hypothesis on the structural and semantic autonomy and lexico­morphosyntactic specialization of adjuncts. Yet, more com­ plicated organization of their network is revealed, pointing to the diversity of adjuncts in terms of their distribution and behavior.

Keywords: Russian language, semantic role labeling, adjunct role labeling, adjunct and predicate embeddings, Russian FrameBank, классификация семантических ролей, определение семантических ролей сирконстан­тов, векторные представления сирконстантов и предикато, ФреймБанк, русский язык

In book

Computational Linguistics and Intellectual Technologies: Papers from the Annual International Conference “Dialogue” (2021)

Issue 20: Основной том. , -, 2021.