Papers by Mikhail Burtsev

12 papers
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (2025.acl-long)

Copied to clipboard

Challenge: Recent work addresses problem of compression of tokens into shorter sequence of real-valued vectors . attainable lossless compression ratio is typically not higher than x10 .
Approach: They propose to compress a sequence of tokens into a shorter sequence of real-valued vectors to be used as inputs instead of token embeddings or key-value cache.
Outcome: The proposed algorithms reduce the amount of compute in existing language models rather than minimizing number of bits needed to store text.
Attention Understands Semantic Relations (2022.lrec-1)

Copied to clipboard

Challenge: Present-day monopoly of foundation language models in most tasks forces researchers and practitioners to rely on popular large models without genuinely understanding the models' behaviour.
Approach: They propose a probing pipeline to study the representedness of semantic relations in transformer language models and propose 'attention mechanisms' that focus on syntactic relational information and semantic one.
Outcome: The proposed pipeline shows that attention scores are expressive as output activations on this task, despite their lesser ability to represent surface cues.
DeepPavlov: Open-Source Library for Dialogue Systems (P18-4)

Copied to clipboard

Challenge: open-source library DeepPavlov is designed for rapid development of dialogue systems.
Approach: open-source library DeepPavlov is tailored for development of conversational agents . the library prioritizes efficiency, modularity and extensibility with the goal to make it easier to develop dialogue systems from scratch .
Outcome: the open-source library DeepPavlov is designed for rapid development of dialogue systems . it supports modular as well as end-to-end approaches to implementation of conversational agents .
Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for text classification tasks are inherently ambiguous and can cause errors.
Approach: They propose a method that combines epistemic and aleatoric uncertainty to estimate toxicity detection errors.
Outcome: The proposed method outperforms existing methods for toxicity detection and other ambiguous text classification tasks.
Uncertainty Guided Global Memory Improves Multi-Hop Question Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Transformers are used to solve multi-hop question answering tasks that require reasoning over multiple parts of a long document.
Approach: They propose a method that collects relevant information over the entire document and then combines it with local context to solve a multi-hop question answering task.
Outcome: The proposed method improves on three MHQA datasets compared to the baseline model.
Uncertainty Estimation of Transformer Predictions for Misclassification Detection (2022.acl-long)

Copied to clipboard

Challenge: Uncertainty estimation (UE) of model predictions is crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, etc.
Approach: They propose to modify UE methods for Transformer models for misclassification detection in named entity recognition and text classification tasks to improve model expressiveness and computational performance.
Outcome: The proposed methods outperform computationally intensive methods on misclassification detection tasks and are based on a large dataset of simulated datasets.
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions (2021.emnlp-main)

Copied to clipboard

Challenge: Recent advances on neural approaches to natural language processing have triggered a renaissance in end-to-end neural open-domain chatbots.
Approach: They propose to use offline and online steps to evaluate the quality of clarifying questions in various open-domain dialogues to improve the quality and accuracy of the system response.
Outcome: The proposed pipeline is suitable as a foundation for further research.
Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information (2023.findings-emnlp)

Copied to clipboard

Challenge: Knowledge graph completion (KGC) methods are computationally intensive and impractical for large-scale KGs.
Approach: They propose to include node neighborhoods as additional information to improve KGC methods based on language models.
Outcome: The proposed method outperforms KGT5 and conventional methods on inductive and transductive Wikidata subsets and shows its importance.
DeepPavlov Dream: Platform for Building Generative AI Assistants (2023.acl-demo)

Copied to clipboard

Challenge: open-source DeepPavlov Dream Platform is designed for development of complex dialog systems . platform supports modular approach to implementation of conversational agents .
Approach: open-source DeepPavlov Dream Platform is designed for development of complex dialog systems . platform includes a conversational orchestrator called DeepPvlov Agent to coordinate asynchronous dialog pipeline .
Outcome: The open-source DeepPavlov Dream Platform is designed for development of complex dialog systems like Generative AI Assistants.
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Knowledge graphs provide structured, verifiable grounding for large language models . current LLMs use KGs as auxiliary structures for text retrieval .
Approach: They propose a pipeline that constructs KGs from open-domain texts using triplets and qualifiers.
Outcome: The proposed pipeline outperforms existing methods in retrieval-augmented generation.
Active Learning for Abstractive Text Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Abstractive text summarization (ATS) requires a long document and short summaries.
Approach: They propose a query strategy for AL in abstractive text summarization that uses uncertainty estimation to reduce model performance.
Outcome: The proposed query strategy improves ROUGE and consistency scores for annotated datasets . it also increases the performance of the model, compared to passive annotation.
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear.
Approach: They evaluate how large language models learn multi-step reasoning without memorization . they find that most neural architectures trained from scratch can learn rule inference .
Outcome: The proposed framework fails to solve a natural-language proxy task with high accuracy.

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