Papers by Daniil Vodolazsky
Constructing a Lexical Resource of Russian Derivational Morphology (2022.lrec-1)
Copied to clipboard
| Challenge: | In Natural Language Processing of Russian, the inflection is satisfactorily processed, but there are only a few machine-trackable resources that capture derivations . |
| Approach: | They propose to use machine-learning methods to improve Russian inflection and derivational resources by using a database of more than 300 thousand lexemes and 164 thousand binary derivations. |
| Outcome: | The proposed method includes more than 300 thousand lexemes connected with more than 164 thousand binary derivational relations. |
DerivBase.Ru: a Derivational Morphology Resource for Russian (2020.lrec-1)
Copied to clipboard
| Challenge: | DerivBase.Ru is a high-coverage derivational morphology resource for Russian language that can be used for many tasks such as paraphrases and plagiarism detection. |
| Approach: | They propose a rule-based framework for deriving Russian words using a derivational morphology resource called DerivBase.Ru. |
| Outcome: | The proposed framework can be used to derivate words from a dictionary in Russian and German. |
2Columns1Row: A Russian Benchmark for Textual and Multimodal Table Understanding and Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | 2Columns1Row is the first open-source benchmark for the table understanding task in Russian. |
| Approach: | They propose a benchmark for table understanding in Russian using textual and multimodal inputs. |
| Outcome: | The proposed benchmark evaluates models' ability to reason about relationships between rows and columns in tables using text-only and multimodal approaches. |