Search Results for author: Natalia Loukachevitch

Found 46 papers, 13 papers with code

Evaluation of Taxonomy Enrichment on Diachronic WordNet Versions

no code implementations EACL (GWC) 2021 Irina Nikishina, Natalia Loukachevitch, Varvara Logacheva, Alexander Panchenko

The vast majority of the existing approaches for taxonomy enrichment apply word embeddings as they have proven to accumulate contexts (in a broad sense) extracted from texts which are sufficient for attaching orphan words to the taxonomy.

Word Embeddings

Comparing Similarity of Words Based on Psychosemantic Experiment and RuWordNet

no code implementations EACL (GWC) 2021 Valery Solovyev, Natalia Loukachevitch

In the paper we compare the structure of the Russian language thesaurus RuWordNet with the data of a psychosemantic experiment to identify semantically close words.

Comparison of Genres in Word Sense Disambiguation using Automatically Generated Text Collections

no code implementations CLIB 2020 Angelina Bolshina, Natalia Loukachevitch

The best approaches in Word Sense Disambiguation (WSD) are supervised and rely on large amounts of hand-labelled data, which is not always available and costly to create.

Word Sense Disambiguation

Comparing Two Thesaurus Representations for Russian

no code implementations GWC 2018 Natalia Loukachevitch, German Lashevich, Boris Dobrov

In the paper we presented a new Russian wordnet, RuWordNet, which was semi-automatically obtained by transformation of the existing Russian thesaurus RuThes.

Vocal Bursts Valence Prediction

Entity Linking over Nested Named Entities for Russian

1 code implementation LREC 2022 Natalia Loukachevitch, Pavel Braslavski, Vladimir Ivanov, Tatiana Batura, Suresh Manandhar, Artem Shelmanov, Elena Tutubalina

In this paper, we describe entity linking annotation over nested named entities in the recently released Russian NEREL dataset for information extraction.

Entity Linking

Linking Russian Wordnet RuWordNet to WordNet

no code implementations GWC 2019 Natalia Loukachevitch, Anastasia Gerasimova

In this paper we consider the linking procedure of Russian wordnet (RuWordNet) to Wordnet.


Thesaurus Verification Based on Distributional Similarities

no code implementations GWC 2019 Natalia Loukachevitch, Ekaterina Parkhomenko

In this paper we consider an approach to verification of large lexical-semantic resources as WordNet.

Large Language Models in Targeted Sentiment Analysis

2 code implementations18 Apr 2024 Nicolay Rusnachenko, Anton Golubev, Natalia Loukachevitch

Reasoning capabilities of the fine-tuned Flan-T5 models with THoR achieve at least 5% increment with the base-size model compared to the results of the zero-shot experiment.

Decoder Sentiment Analysis

Exploring Prompt-Based Methods for Zero-Shot Hypernym Prediction with Large Language Models

no code implementations9 Jan 2024 Mikhail Tikhomirov, Natalia Loukachevitch

This article investigates a zero-shot approach to hypernymy prediction using large language models (LLMs).

Language Modelling

RuSentNE-2023: Evaluating Entity-Oriented Sentiment Analysis on Russian News Texts

1 code implementation28 May 2023 Anton Golubev, Nicolay Rusnachenko, Natalia Loukachevitch

The paper describes the RuSentNE-2023 evaluation devoted to targeted sentiment analysis in Russian news texts.

Sentence Sentiment Analysis

RuArg-2022: Argument Mining Evaluation

no code implementations18 Jun 2022 Evgeny Kotelnikov, Natalia Loukachevitch, Irina Nikishina, Alexander Panchenko

Argumentation analysis is a field of computational linguistics that studies methods for extracting arguments from texts and the relationships between them, as well as building argumentation structure of texts.

Argument Mining Natural Language Inference +1

Taxonomy Enrichment with Text and Graph Vector Representations

no code implementations21 Jan 2022 Irina Nikishina, Mikhail Tikhomirov, Varvara Logacheva, Yuriy Nazarov, Alexander Panchenko, Natalia Loukachevitch

With the rapid growth of lexical resources for specific domains, the problem of automatic extension of the existing knowledge bases with new words is becoming more and more widespread.

Knowledge Graphs Word Embeddings

Transfer Learning for Improving Results on Russian Sentiment Datasets

1 code implementation6 Jul 2021 Anton Golubev, Natalia Loukachevitch

In this study, we test transfer learning approach on Russian sentiment benchmark datasets using additional train sample created with distant supervision technique.

Natural Language Inference Sentiment Analysis +2

Improving Results on Russian Sentiment Datasets

1 code implementation28 Jul 2020 Anton Golubev, Natalia Loukachevitch

In this study, we test standard neural network architectures (CNN, LSTM, BiLSTM) and recently appeared BERT architectures on previous Russian sentiment evaluation datasets.

Natural Language Inference Sentiment Analysis +1

Attention-Based Neural Networks for Sentiment Attitude Extraction using Distant Supervision

2 code implementations23 Jun 2020 Nicolay Rusnachenko, Natalia Loukachevitch

In this paper, we provide a study on attention-based context encoders in the sentiment attitude extraction task.

General Classification

Studying Attention Models in Sentiment Attitude Extraction Task

4 code implementations20 Jun 2020 Nicolay Rusnachenko, Natalia Loukachevitch

In this paper, we provide a study on attention-based context encoders in the sentiment attitude extraction task.

Sentiment Frames for Attitude Extraction in Russian

1 code implementation19 Jun 2020 Natalia Loukachevitch, Nicolay Rusnachenko

Texts can convey several types of inter-related information concerning opinions and attitudes.

RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the Russian language

no code implementations22 May 2020 Irina Nikishina, Varvara Logacheva, Alexander Panchenko, Natalia Loukachevitch

This paper describes the results of the first shared task on taxonomy enrichment for the Russian language.

Distant Supervision for Sentiment Attitude Extraction

no code implementations RANLP 2019 Nicolay Rusnachenko, Natalia Loukachevitch, Elena Tutubalina

News articles often convey attitudes between the mentioned subjects, which is essential for understanding the described situation.

Corpus-based Check-up for Thesaurus

no code implementations ACL 2019 Natalia Loukachevitch

In this paper we discuss the usefulness of applying a checking procedure to existing thesauri.

Extracting Sentiment Attitudes From Analytical Texts

3 code implementations27 Aug 2018 Natalia Loukachevitch, Nicolay Rusnachenko

In this paper we present the RuSentRel corpus including analytical texts in the sphere of international relations.

BIG-bench Machine Learning

RUSSE: The First Workshop on Russian Semantic Similarity

no code implementations15 Mar 2018 Alexander Panchenko, Natalia Loukachevitch, Dmitry Ustalov, Denis Paperno, Christian Meyer, Natalia Konstantinova

The paper gives an overview of the Russian Semantic Similarity Evaluation (RUSSE) shared task held in conjunction with the Dialogue 2015 conference.

Semantic Similarity Semantic Textual Similarity

Human Associations Help to Detect Conventionalized Multiword Expressions

no code implementations RANLP 2017 Natalia Loukachevitch, Anastasia Gerasimova

In this paper we show that if we want to obtain human evidence about conventionalization of some phrases, we should ask native speakers about associations they have to a given phrase and its component words.

Combining Thesaurus Knowledge and Probabilistic Topic Models

no code implementations31 Jul 2017 Natalia Loukachevitch, Michael Nokel, Kirill Ivanov

In this paper we present the approach of introducing thesaurus knowledge into probabilistic topic models.

Topic Models

Summarizing News Clusters on the Basis of Thematic Chains

no code implementations LREC 2014 Natalia Loukachevitch, Aleksey Alekseev

In this paper we consider a method for extraction of sets of semantically similar language expressions representing different partici-pants of the text story ― thematic chains.

Document Summarization Multi-Document Summarization +2

Automatic Term Recognition Needs Multiple Evidence

no code implementations LREC 2012 Natalia Loukachevitch

In this paper we argue that the automatic term extraction procedure is an inherently multifactor process and the term extraction models needs to be based on multiple features including a specific type of a terminological resource under development.

Information Retrieval Term Extraction

Cannot find the paper you are looking for? You can Submit a new open access paper.