L
Lasha Abzianidze
Researcher at University of Groningen
Publications - 36
Citations - 672
Lasha Abzianidze is an academic researcher from University of Groningen. The author has contributed to research in topics: Parsing & Natural language. The author has an hindex of 13, co-authored 34 publications receiving 535 citations. Previous affiliations of Lasha Abzianidze include Tilburg University & Utrecht University.
Papers
More filters
Proceedings ArticleDOI
The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations
Lasha Abzianidze,Johannes Bjerva,Kilian Evang,Hessel Haagsma,Rik van Noord,Pierre Ludmann,Duc-Duy Nguyen,Johannes Bos +7 more
TL;DR: The approach is based on cross-lingual projection: automatically produced (and manually corrected) semantic annotations for English sentences are mapped onto their word-aligned translations, assuming that the translations are meaning-preserving.
Posted Content
The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations
Lasha Abzianidze,Johannes Bjerva,Kilian Evang,Hessel Haagsma,Rik van Noord,Pierre Ludmann,Duc-Duy Nguyen,Johannes Bos +7 more
TL;DR: The Parallel Meaning Bank as mentioned in this paper is a corpus of translations annotated with shared, formal meaning representations comprising over 11 million words divided over four languages (English, German, Italian, and Dutch).
Proceedings ArticleDOI
A Tableau Prover for Natural Logic and Language
TL;DR: A theorem prover for Natural Logic, a logic whose terms resemble natural language expressions based on an analytic tableau method and employs syntactically and semantically motivated schematic rules is designed.
Journal ArticleDOI
Exploring Neural Methods for Parsing Discourse Representation Structures
TL;DR: This work presents a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers.
Towards Universal Semantic Tagging
Lasha Abzianidze,Johan Bos +1 more
TL;DR: This article proposed the task of universal semantic tagging and showed that the tags provide semantically fine-grained information, and they are suitable for cross-lingual semantic parsing, which contributes to better semantic analysis for multilingual text.