Papers by Ekaterina Taktasheva

4 papers
A Family of Pretrained Transformer Language Models for Russian (2024.lrec-main)

Copied to clipboard

Challenge: Developing Transformer language models for the Russian language has received little attention . most of these LMs are developed for English, which imposes substantial constraints on the potential of the language technologies.
Approach: They propose to release 13 Russian Transformer language models that span three languages . they aim to broaden the scope of NLP research directions and develop industrial solutions for the Russian language.
Outcome: The proposed models are based on Russian language datasets and benchmarks.
TAPE: Assessing Few-shot Russian Language Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in zero-shot and few-shot learning have shown promise for a scope of research and practical purposes, but lacks standardized evaluation suites for non-English languages.
Approach: They propose a novel benchmark that includes six more complex NLU tasks for Russian, covering multi-hop reasoning, ethical concepts, logic and commonsense knowledge.
Outcome: The proposed benchmark includes six more complex NLU tasks for Russian, covering multi-hop reasoning, ethical concepts, logic and commonsense knowledge.
TAPS: Tool-Augmented Personalisation via Structured Tagging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to personalise tool use overlook the role of personalisation in guiding tool use.
Approach: They propose a tool-augmented large language model that integrates user preferences into goal-oriented dialogue agents by leveraging a structured tagging tool and an uncertainty-based tool detector.
Outcome: The proposed solution significantly improves the ability of LLMs to incorporate user preferences, achieving the new state-of-the-art for open source models on the NLSI task.
RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing resources for minimal pairs address a limited number of languages and lack diversity of language-specific grammatical phenomena.
Approach: They propose to use a Russian benchmark of linguistic minimal pairs to evaluate grammatical knowledge of language models.
Outcome: The proposed benchmark includes 45k pairs of sentences that differ in grammaticality and isolate a morphological, syntactic, or semantic phenomenon.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations