Papers by Andrey Kutuzov

16 papers
NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark (2025.findings-acl)

Copied to clipboard

Challenge: NorEval is a new evaluation suite for large-scale standardized benchmarking of Norwegian generative language models (LMs).
Approach: They propose a new evaluation suite for large-scale standardized benchmarking of Norwegian generative language models (LMs) NorEval consists of 24 high-quality human-created datasets, of which five are created from scratch.
Outcome: The evaluation framework and materials are publicly available.
Representing ELMo embeddings as two-dimensional text online (2021.eacl-demos)

Copied to clipboard

Challenge: ELMoViz module adds support for contextualized embedding architectures, in particular for token embeddable word models.
Approach: They propose to add a module to the free and open-source WebVectors toolkit which provides lexical hyperlinks to word representations in static embedding models.
Outcome: The ELMoViz module adds support for contextualized embedding architectures, in particular for ELMa models.
A New Massive Multilingual Dataset for High-Performance Language Technologies (2024.lrec-main)

Copied to clipboard

Challenge: a new massive multilingual dataset is available for language modeling and machine translation training.
Approach: They present a massive multilingual dataset using web crawls from the Internet Archive and CommonCrawl . they use open-source software tools and high-performance computing to acquire, manage and process large corpora .
Outcome: The HPLT language resources is a massive multilingual dataset . it includes monolingual and bilingual corpora extracted from CommonCrawl and the Internet Archive . the results are published online at the journal journal cense4 .
Making Fast Graph-based Algorithms with Graph Metric Embeddings (P19-1)

Copied to clipboard

Challenge: Graph measures, such as node distances, are inefficient to compute.
Approach: They propose a way to learn graph embeddings by using vector operations instead of a graph structure.
Outcome: The proposed method outperforms other graph embeddings on word similarity and word sense disambiguation tasks.
Enriching Word Usage Graphs with Cluster Definitions (2024.lrec-main)

Copied to clipboard

Challenge: Existing word usage graphs lack human interpretability of senses.
Approach: They propose to enrich existing word usage graphs with cluster labels functioning as sense definitions.
Outcome: The proposed dataset matches the definitions chosen from WordNet by two baseline systems.
Explaining novel senses using definition generation with open language models (2025.findings-emnlp)

Copied to clipboard

Challenge: We apply definition generators based on open-weights large language models to create explanations of novel senses.
Approach: They apply open-weights large language models to create explanations of novel senses using target word usages as input.
Outcome: The proposed definition generators perform on par with decoder-only models.
An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT) (2025.acl-long)

Copied to clipboard

Challenge: a large number of textual data is needed to train state-of-the-art large language models.
Approach: They propose a collection of monolingual and parallel corpora from the Internet Archive . they document the entire data pipeline and release the code to reproduce it .
Outcome: The proposed collection of monolingual and parallel corpora is based on the HPLT v2 dataset . it includes 8T tokens covering 193 languages and 380M sentence pairs covering 51 languages .
Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to semantic change analysis are limited in their interpretation power and lack of explanatory power.
Approach: They propose to use specialised Flan-T5 language models to generate a definition for each usage and a specialised word sense model to generate the most prototypical definition.
Outcome: The proposed representations outperform token or usage sentence embeddings in word-in-context semantic similarity judgements and are a promising type of lexical representation for NLP.
Diachronic word embeddings and semantic shifts: a survey (C18-1)

Copied to clipboard

Challenge: Existing methods for tracing time-related semantic shifts with word embedding models lack the cohesion, common terminology and shared practices of more established areas of natural language processing.
Approach: They propose several axes along which these methods can be compared and propose a framework for comparison.
Outcome: The proposed methods are compared with existing methods and outline their main challenges and potential applications.
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca (2024.findings-eacl)

Copied to clipboard

Challenge: Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants.
Approach: They employ a dataset and machine translations of it to form multilingual data and use it to tune LLMs.
Outcome: The proposed model is on par or better than a model for each language, and multilingual tuning with downsampled data is as powerful and robust.
Definition generation for lexical semantic change detection (2024.findings-acl)

Copied to clipboard

Challenge: a number of studies have attempted to bridge the gap between lexical semantic change detection and sense-based LSCD methods.
Approach: They propose a sense distribution based LSCD method which uses contextualized word definitions as 'senses' they argue that the method preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-sense.
Outcome: The proposed method outperforms previous sense-based methods on five datasets and three languages and preserves interpretability and allows to inspect the reasons behind a specific shift in terms of discrete definitions-as-senses.
Unsupervised Semantic Frame Induction using Triclustering (P18-2)

Copied to clipboard

Challenge: Recent work on frame-semantics has enabled the development of wide-coverage frame parsers using supervised learning.
Approach: They propose to use dependency triples to perform unsupervised frame induction on a Web-scale corpus.
Outcome: The proposed approach performs state-of-the-art on a FrameNet-derived dataset and performs on par with competitive methods on . verb class clustering task.
RuSemShift: a dataset of historical lexical semantic change in Russian (2020.coling-main)

Copied to clipboard

Challenge: et al. (2017) lexical semantic change analysis is still mostly done for English because of limited resources.
Approach: They present a large-scale manually annotated test set for semantic change modeling in Russian . they use DURel framework to annotate Russian for two long-term time periods .
Outcome: The proposed model performs well, but there are still areas for improvement . the results are promising, but the authors say they need to improve .
NorDiaChange: Diachronic Semantic Change Dataset for Norwegian (2022.lrec-1)

Copied to clipboard

Challenge: NorDiaChange is the first dataset of diachronic semantic change on the lexical level for Norwegian.
Approach: They describe a manual annotation process for a new dataset of diachronic semantic change for Norwegian.
Outcome: The proposed dataset covers the time periods related to pre- and post-war events, oil and gas discovery in Norway, and technological developments.
Trained on 100 million words and still in shape: BERT meets British National Corpus (2023.findings-eacl)

Copied to clipboard

Challenge: masked language models are trained on ever larger corpora, but pre-training on a modestly-sized but representative, well-balanced, and publicly available corpus can reach better performance than the original BERT model.
Approach: They propose an optimized LM architecture called LTG-BERT that can be used to train a competitive language model on a small and standardizable corpus.
Outcome: The proposed architecture outperforms the original English BERT model on a representative, well-balanced and publicly available corpus.
Word Sense Disambiguation for 158 Languages using Word Embeddings Only (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods of disambiguation of word senses are based on knowledge bases, taxonomies, and other externally built resources.
Approach: They propose a method that takes a pre-trained word embedding model and induces a fully-fledged word sense inventory for 158 languages.
Outcome: The proposed model is based on a pre-trained word embedding model and induces a fully-fledged word sense inventory in 158 languages.

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