Search Results for author:
Found 35 papers, 11 papers with code
A large-scale computational study of content preservation measures for text style transfer and paraphrase generation
In both tasks, the system is supposed to generate a text which should be semantically similar to the input text.
ParaDetox: Detoxification with Parallel Data
To the best of our knowledge, these are the first parallel datasets for this task. We describe our pipeline in detail to make it fast to set up for a new language or domain, thus contributing to faster and easier development of new parallel resources. We train several detoxification models on the collected data and compare them with several baselines and state-of-the-art unsupervised approaches.
Evaluation of Taxonomy Enrichment on Diachronic WordNet Versions
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.
A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification
It is often difficult to reliably evaluate models which generate text.
RuPAWS: A Russian Adversarial Dataset for Paraphrase Identification
We compare it to the largest available dataset for Russian ParaPhraser and show that the best available paraphrase identifiers for the Russian language fail on the RuPAWS dataset.
Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company’s Reputation
We define a set of sensitive topics that can yield inappropriate and toxic messages and describe the methodology of collecting and labelling a dataset for appropriateness.
Studying the role of named entities for content preservation in text style transfer
Text style transfer techniques are gaining popularity in Natural Language Processing, finding various applications such as text detoxification, sentiment, or formality transfer.
Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language
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.
Taxonomy Enrichment with Text and Graph Vector Representations
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.
Text Detoxification using Large Pre-trained Neural Models
We compare our models with a number of methods for style transfer.
SkoltechNLP at SemEval-2021 Task 5: Leveraging Sentence-level Pre-training for Toxic Span Detection
We show that fine-tuning a RoBERTa model for this problem is a strong baseline.
Methods for Detoxification of Texts for the Russian Language
We introduce the first study of automatic detoxification of Russian texts to combat offensive language.
Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation
We define a set of sensitive topics that can yield inappropriate and toxic messages and describe the methodology of collecting and labeling a dataset for appropriateness.
Studying Taxonomy Enrichment on Diachronic WordNet Versions
Ontologies, taxonomies, and thesauri are used in many NLP tasks.
RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the Russian language
This paper describes the results of the first shared task on taxonomy enrichment for the Russian language.
Word Sense Disambiguation for 158 Languages using Word Embeddings Only
We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al. (2018), enabling WSD in these languages.
MIPT System for World-Level Quality Estimation
We explore different model architectures for the WMT 19 shared task on word-level quality estimation of automatic translation.
The Second Conversational Intelligence Challenge (ConvAI2)
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots.
Few-shot classification in Named Entity Recognition Task
For many natural language processing (NLP) tasks the amount of annotated data is limited.
Robust Word Vectors: Context-Informed Embeddings for Noisy Texts
We suggest a new language-independent architecture of robust word vectors (RoVe).
Findings of the WMT 2018 Shared Task on Quality Estimation
We report the results of the WMT18 shared task on Quality Estimation, i. e. the task of predicting the quality of the output of machine translation systems at various granularity levels: word, phrase, sentence and document.
DeepPavlov: Open-Source Library for Dialogue Systems
It supports modular as well as end-to-end approaches to implementation of conversational agents.
MARMOT: A Toolkit for Translation Quality Estimation at the Word Level
The tool has a set of state-of-the-art features for QE, and new features can easily be added.
Phrase Level Segmentation and Labelling of Machine Translation Errors
This paper presents our work towards a novel approach for Quality Estimation (QE) of machine translation based on sequences of adjacent words, the so-called phrases.
A Quality-based Active Sample Selection Strategy for Statistical Machine Translation
Our approach is based on a quality estimation technique which involves a wider range of features of the source text, automatic translation, and machine translation system compared to previous work.
