Search Results for author:
Found 36 papers, 10 papers with code
InFoBERT: Zero-Shot Approach to Natural Language Understanding Using Contextualized Word Embedding
Natural language understanding is an important task in modern dialogue systems.
Multiple Teacher Distillation for Robust and Greener Models
The language models nowadays are in the center of natural language processing progress.
Single Example Can Improve Zero-Shot Data Generation
We explore two approaches to the generation of task-oriented utterances: in the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training.
Findings of the LoResMT 2020 Shared Task on Zero-Shot for Low-Resource languages
This paper presents the findings of the LoResMT 2020 Shared Task on zero-shot translation for low resource languages.
Ask Me Anything in Your Native Language
Cross-lingual question answering is a thriving field in the modern world, helping people to search information on the web more efficiently.
CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement
Effective generation of structured code comments requires robust quality metrics for dataset curation, yet existing approaches (SIDE, MIDQ, STASIS) suffer from limited code-comment analysis.
StRuCom: A Novel Dataset of Structured Code Comments in Russian
Structured code comments in docstring format are essential for code comprehension and maintenance, but existing machine learning models for their generation perform poorly for Russian compared to English.
ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations
In contrast to conventional pruning approaches that require additional training or fine-tuning, our approach requires only a small calibration dataset that is used to estimate a linear transformation to approximate the pruned blocks.
Iterative Self-Training for Code Generation via Reinforced Re-Ranking
One effective way to enhance code generation is by pairing a code generation model with a reranker model, which selects the best solution from the generated samples.
Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
Machine translation for low resource language pairs is a challenging task.
SumHiS: Extractive Summarization Exploiting Hidden Structure
We introduce a new approach to extractive summarization task using hidden clustering structure of the text.
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.
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.
CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search
We consider the well-known and important tasks of clone detection and information retrieval for source code.
Searching by Code: a New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets
Code search is an important and well-studied task, but it usually means searching for code by a text query.
DetIE: Multilingual Open Information Extraction Inspired by Object Detection
Our model sets the new state of the art performance of 67. 7% F1 on CaRB evaluated as OIE2016 while being 3. 35x faster at inference than previous state of the art.
Ranked #1 on
Open Information Extraction
on LSOIE
Template-based Approach to Zero-shot Intent Recognition
We outperform previous state-of-the-art f1-measure by up to 16\% for unseen intents, using intent labels and user utterances and without accessing external sources (such as knowledge bases).
WikiMulti: a Corpus for Cross-Lingual Summarization
Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models
In the last year, new neural architectures and multilingual pre-trained models have been released for Russian, which led to performance evaluation problems across a range of language understanding tasks.
A Single Example Can Improve Zero-Shot Data Generation
In the zero-shot approach, the model is trained to generate utterances from seen intents and is further used to generate utterances for intents unseen during training.
How not to Lie with a Benchmark: Rearranging NLP Learderboards
Proper model ranking and comparison with a human level is an essential requirement for every benchmark to be a reliable measurement of the model quality.
MOROCCO: Model Resource Comparison Framework
The new generation of pre-trained NLP models push the SOTA to the new limits, but at the cost of computational resources, to the point that their use in real production environments is often prohibitively expensive.
SumTitles: a Summarization Dataset with Low Extractiveness
The existing dialogue summarization corpora are significantly extractive.
RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
In this paper, we introduce an advanced Russian general language understanding evaluation benchmark -- RussianGLUE.
Ranked #1 on
Word Sense Disambiguation
on RUSSE
Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification
Deep learning architectures based on self-attention have recently achieved and surpassed state of the art results in the task of unsupervised aspect extraction and topic modeling.
Humans Keep It One Hundred: an Overview of AI Journey
Artificial General Intelligence (AGI) is showing growing performance in numerous applications - beating human performance in Chess and Go, using knowledge bases and text sources to answer questions (SQuAD) and even pass human examination (Aristo project).
The Russian Drug Reaction Corpus and Neural Models for Drug Reactions and Effectiveness Detection in User Reviews
For the sentence classification task, our model achieves the macro F1 score of 68. 82% gaining 7. 47% over the score of BERT model trained on Russian data.
RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback
Recent research has shown the advantages of using autoencoders based on deep neural networks for collaborative filtering.
Ranked #1 on
Recommendation Systems
on MovieLens 20M
(Recall@50 metric)
AspeRa: Aspect-Based Rating Prediction Based on User Reviews
We propose a novel Aspect-based Rating Prediction model (AspeRa) that estimates user rating based on review texts for the items.
Robust to Noise Models in Natural Language Processing Tasks
There are a lot of noise texts surrounding a person in modern life.
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.
Self-Attentive Model for Headline Generation
Headline generation is a special type of text summarization task.
AspeRa: Aspect-based Rating Prediction Model
We propose a novel end-to-end Aspect-based Rating Prediction model (AspeRa) that estimates user rating based on review texts for the items and at the same time discovers coherent aspects of reviews that can be used to explain predictions or profile users.
Sequence Learning with RNNs for Medical Concept Normalization in User-Generated Texts
In this work, we consider the medical concept normalization problem, i. e., the problem of mapping a disease mention in free-form text to a concept in a controlled vocabulary, usually to the standard thesaurus in the Unified Medical Language System (UMLS).
Robust Word Vectors: Context-Informed Embeddings for Noisy Texts
We suggest a new language-independent architecture of robust word vectors (RoVe).
DeepPavlov: Open-Source Library for Dialogue Systems
It supports modular as well as end-to-end approaches to implementation of conversational agents.
