Search Results - "Logacheva, Varvara"
-
1
Methods for Detoxification of Texts for the Russian Language
Published in Multimodal technologies and interaction (01-09-2021)“…We introduce the first study of the automatic detoxification of Russian texts to combat offensive language. This kind of textual style transfer can be used for…”
Get full text
Journal Article -
2
Beyond plain toxic: building datasets for detection of flammable topics and inappropriate statements
Published in Language resources and evaluation (01-06-2024)“…Toxicity on the Internet is an acknowledged problem. It includes a wide range of actions from the use of obscene words to offenses and hate speech toward…”
Get full text
Journal Article -
3
Human feedback in statistical machine translation
Published 01-01-2017“…The thesis addresses the challenge of improving Statistical Machine Translation (SMT) systems via feedback given by humans on translation quality. The amount…”
Get full text
Dissertation -
4
Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language
Published 04-03-2022“…Toxicity on the Internet, such as hate speech, offenses towards particular users or groups of people, or the use of obscene words, is an acknowledged problem…”
Get full text
Journal Article -
5
Studying the role of named entities for content preservation in text style transfer
Published 20-06-2022“…Natural Language Processing and Information Systems. NLDB 2022. Lecture Notes in Computer Science, vol 13286. Springer, Cham, p.437--448 Text style transfer…”
Get full text
Journal Article -
6
Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation
Published 09-03-2021“…Not all topics are equally "flammable" in terms of toxicity: a calm discussion of turtles or fishing less often fuels inappropriate toxic dialogues than a…”
Get full text
Journal Article -
7
Studying Taxonomy Enrichment on Diachronic WordNet Versions
Published 23-11-2020“…Ontologies, taxonomies, and thesauri are used in many NLP tasks. However, most studies are focused on the creation of these lexical resources rather than the…”
Get full text
Journal Article -
8
Few-shot classification in Named Entity Recognition Task
Published 14-12-2018“…For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such…”
Get full text
Journal Article -
9
RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the Russian language
Published 22-05-2020“…This paper describes the results of the first shared task on taxonomy enrichment for the Russian language. The participants were asked to extend an existing…”
Get full text
Journal Article -
10
Taxonomy Enrichment with Text and Graph Vector Representations
Published 21-01-2022“…Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in…”
Get full text
Journal Article -
11
Text Detoxification using Large Pre-trained Neural Models
Published 18-09-2021“…We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process…”
Get full text
Journal Article -
12
Methods for Detoxification of Texts for the Russian Language
Published 19-05-2021“…We introduce the first study of automatic detoxification of Russian texts to combat offensive language. Such a kind of textual style transfer can be used, for…”
Get full text
Journal Article -
13
Word Sense Disambiguation for 158 Languages using Word Embeddings Only
Published 14-03-2020“…Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based…”
Get full text
Journal Article -
14
The Second Conversational Intelligence Challenge (ConvAI2)
Published 31-01-2019“…We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways…”
Get full text
Journal Article