Search Results for author:
Found 86 papers, 43 papers with code
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.
SkoltechNLP at SemEval-2022 Task 8: Multilingual News Article Similarity via Exploration of News Texts to Vector Representations
This paper describes our contribution to SemEval 2022 Task 8: Multilingual News Article Similarity.
Pixel-Level BPE for Auto-Regressive Image Generation
Pixel-level autoregression with Transformer models (Image GPT or iGPT) is one of the recent approaches to image generation that has not received massive attention and elaboration due to quadratic complexity of attention as it imposes huge memory requirements and thus restricts the resolution of the generated images.
Cross-Modal Contextualized Hidden State Projection Method for Expanding of Taxonomic Graphs
We propose a method that combines graph-, and text-based contextualized representations from transformer networks to predict new entries 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.
Exploring Cross-lingual Text Detoxification with Large Multilingual Language Models.
This work investigates multilingual and cross-lingual detoxification and the behavior of large multilingual models in this setting.
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.
Uncertainty Estimation of Transformer Predictions for Misclassification Detection
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc.
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.
Generating Lexical Representations of Frames using Lexical Substitution
We investigate a simple yet effective method, lexical substitution with word representation models, to automatically expand a small set of frame-annotated sentences with new words for their respective roles and LUs.
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.
Multilingual and Explainable Text Detoxification with Parallel Corpora
Even with various regulations in place across countries and social media platforms (Government of India, 2021; European Parliament and Council of the European Union, 2022, digital abusive speech remains a significant issue.
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
The performance of Transformer models has been enhanced by increasing the number of parameters and the length of the processed text.
Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
While being one of the most popular question types, simple questions such as "Who is the author of Cinderella?
Unconditional Truthfulness: Learning Conditional Dependency for Uncertainty Quantification of Large Language Models
Uncertainty quantification (UQ) is a perspective approach to detecting Large Language Model (LLM) hallucinations and low quality output.
Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management
Despite regulations imposed by nations and social media platforms, such as recent EU regulations targeting digital violence, abusive content persists as a significant challenge.
S3: A Simple Strong Sample-effective Multimodal Dialog System
In this work, we present a conceptually simple yet powerful baseline for the multimodal dialog task, an S3 model, that achieves near state-of-the-art results on two compelling leaderboards: MMMU and AI Journey Contest 2023.
Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10. 7B parameters), making them computationally expensive and inaccessible to researchers with limited resources.
SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection
In this paper, we present our novel systems developed for the SemEval-2024 hallucination detection task.
MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages
Text detoxification is a textual style transfer (TST) task where a text is paraphrased from a toxic surface form, e. g. featuring rude words, to the neutral register.
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks
It achieves 11 SotA results, 4 top-2 results out of 16 tasks for the Taxonomy Enrichment, Hypernym Discovery, Taxonomy Construction, and Lexical Entailment tasks.
Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output.
MERA: A Comprehensive LLM Evaluation in Russian
To address these issues, we introduce an open Multimodal Evaluation of Russian-language Architectures (MERA), a new instruction benchmark for evaluating foundation models oriented towards the Russian language.
Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification
Text detoxification is the task of transferring the style of text from toxic to neutral.
LM-Polygraph: Uncertainty Estimation for Language Models
Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields.
Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs
Pre-trained Text-to-Text Language Models (LMs), such as T5 or BART yield promising results in the Knowledge Graph Question Answering (KGQA) task.
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
Text-to-image generation is a significant domain in modern computer vision and has achieved substantial improvements through the evolution of generative architectures.
Ranked #19 on
Text-to-Image Generation
on MS COCO
Large Language Models Meet Knowledge Graphs to Answer Factoid Questions
Recently, it has been shown that the incorporation of structured knowledge into Large Language Models significantly improves the results for a variety of NLP tasks.
Don't lose the message while paraphrasing: A study on content preserving style transfer
Text style transfer techniques are gaining popularity in natural language processing allowing paraphrasing text in the required form: from toxic to neural, from formal to informal, from old to the modern English language, etc.
Efficient GPT Model Pre-training using Tensor Train Matrix Representation
On the downstream tasks, including language understanding and text summarization, the model performs similarly to the original GPT-2 model.
Retrieving Comparative Arguments using Ensemble Methods and Neural Information Retrieval
In this paper, we present a submission to the Touche lab's Task 2 on Argument Retrieval for Comparative Questions.
Active Learning for Abstractive Text Summarization
Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance.
Error syntax aware augmentation of feedback comment generation dataset
This paper presents a solution to the GenChal 2022 shared task dedicated to feedback comment generation for writing learning.
Multiverse: Multilingual Evidence for Fake News Detection
In this work, we propose Multiverse -- a new feature based on multilingual evidence that can be used for fake news detection and improve existing approaches.
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.
RuArg-2022: Argument Mining Evaluation
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.
Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution
Lexical substitution, i. e. generation of plausible words that can replace a particular target word in a given context, is an extremely powerful technology that can be used as a backbone of various NLP applications, including word sense induction and disambiguation, lexical relation extraction, data augmentation, etc.
Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models
However, models are not able to perform cross-lingual detoxification and direct fine-tuning on exact language is inevitable.
MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering
Knowledge Graphs (KGs) are symbolically structured storages of facts.
Detecting Text Formality: A Study of Text Classification Approaches
Formality is one of the important characteristics of text documents.
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.
Cross-lingual Evidence Improves Monolingual Fake News Detection
Misleading information spreads on the Internet at an incredible speed, which can lead to irreparable consequences in some cases.
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.
SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task
In our experiments, we used a neural system based on the XLM-R, a pre-trained transformer-based masked language model, as a 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.
How Certain is Your Transformer?
In this work, we consider the problem of uncertainty estimation for Transformer-based models.
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.
Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates
Annotating training data for sequence tagging of texts is usually very time-consuming.
SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection
This paper presents a solution for the Span Identification (SI) task in the {``}Detection of Propaganda Techniques in News Articles{''} competition at SemEval-2020.
Studying Taxonomy Enrichment on Diachronic WordNet Versions
Ontologies, taxonomies, and thesauri are used in many NLP tasks.
Neural Entity Linking: A Survey of Models Based on Deep Learning
This survey presents a comprehensive description of recent neural entity linking (EL) systems developed since 2015 as a result of the "deep learning revolution" in natural language processing.
A Comparative Study of Lexical Substitution Approaches based on Neural Language Models
Lexical substitution in context is an extremely powerful technology that can be used as a backbone of various NLP applications, such as word sense induction, lexical relation extraction, data augmentation, etc.
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.
Making Fast Graph-based Algorithms with Graph Metric Embeddings
The computation of distance measures between nodes in graphs is inefficient and does not scale to large graphs.
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar\'e embeddings in addition to the distributional information to detect compositionality for noun phrases.
Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
We introduce the use of Poincar\'e embeddings to improve existing state-of-the-art approaches to domain-specific taxonomy induction from text as a signal for both relocating wrong hyponym terms within a (pre-induced) taxonomy as well as for attaching disconnected terms in a taxonomy.
HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings
We present our system for semantic frame induction that showed the best performance in Subtask B. 1 and finished as the runner-up in Subtask A of the SemEval 2019 Task 2 on unsupervised semantic frame induction (QasemiZadeh et al., 2019).
Answering Comparative Questions: Better than Ten-Blue-Links?
We present CAM (comparative argumentative machine), a novel open-domain IR system to argumentatively compare objects with respect to information extracted from the Common Crawl.
Unsupervised Sense-Aware Hypernymy Extraction
In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction.
Categorizing Comparative Sentences
We tackle the tasks of automatically identifying comparative sentences and categorizing the intended preference (e. g., "Python has better NLP libraries than MATLAB" => (Python, better, MATLAB).
Sentiment Index of the Russian Speaking Facebook
A sentiment index measures the average emotional level in a corpus.
Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction
We present a detailed theoretical and computational analysis of the Watset meta-algorithm for fuzzy graph clustering, which has been found to be widely applicable in a variety of domains.
Learning Graph Embeddings from WordNet-based Similarity Measures
We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities.
How much does a word weigh? Weighting word embeddings for word sense induction
The paper describes our participation in the first shared task on word sense induction and disambiguation for the Russian language RUSSE'2018 (Panchenko et al., 2018).
Unsupervised Semantic Frame Induction using Triclustering
We use dependency triples automatically extracted from a Web-scale corpus to perform unsupervised semantic frame induction.
An Unsupervised Word Sense Disambiguation System for Under-Resourced Languages
The sparse mode uses the traditional vector space model to estimate the most similar word sense corresponding to its context.
Neologisms on Facebook
In this paper, we present a study of neologisms and loan words frequently occurring in Facebook user posts.
RUSSE: The First Workshop on Russian Semantic Similarity
The paper gives an overview of the Russian Semantic Similarity Evaluation (RUSSE) shared task held in conjunction with the Dialogue 2015 conference.
Enriching Frame Representations with Distributionally Induced Senses
We introduce a new lexical resource that enriches the Framester knowledge graph, which links Framnet, WordNet, VerbNet and other resources, with semantic features from text corpora.
RUSSE'2018: A Shared Task on Word Sense Induction for the Russian Language
The paper describes the results of the first shared task on word sense induction (WSI) for the Russian language.
A Framework for Enriching Lexical Semantic Resources with Distributional Semantics
While both kinds of semantic resources are available with high lexical coverage, our aligned resource combines the domain specificity and availability of contextual information from distributional models with the conciseness and high quality of manually crafted lexical networks.
Improving Hypernymy Extraction with Distributional Semantic Classes
In this paper, we show how distributionally-induced semantic classes can be helpful for extracting hypernyms.
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl
We present DepCC, the largest-to-date linguistically analyzed corpus in English including 365 million documents, composed of 252 billion tokens and 7. 5 billion of named entity occurrences in 14. 3 billion sentences from a web-scale crawl of the \textsc{Common Crawl} project.
Human and Machine Judgements for Russian Semantic Relatedness
On the one hand, humans easily make judgments about semantic relatedness.
Fighting with the Sparsity of Synonymy Dictionaries
Graph-based synset induction methods, such as MaxMax and Watset, induce synsets by performing a global clustering of a synonymy graph.
Making Sense of Word Embeddings
We present a simple yet effective approach for learning word sense embeddings.
Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation
In word sense disambiguation (WSD), knowledge-based systems tend to be much more interpretable than knowledge-free counterparts as they rely on the wealth of manually-encoded elements representing word senses, such as hypernyms, usage examples, and images.
Negative Sampling Improves Hypernymy Extraction Based on Projection Learning
We present a new approach to extraction of hypernyms based on projection learning and word embeddings.
Watset: Automatic Induction of Synsets from a Graph of Synonyms
This paper presents a new graph-based approach that induces synsets using synonymy dictionaries and word embeddings.
