Natural Language Processing

rudetoxifier

Code and data of "Methods for Detoxification of Texts for the Russian Language" paper

detox

Models for automatically transforming toxic text to neutral

inappropriate-sensitive-topics

BSNLP 2021

paradetox

Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"

mutual_implication_score

multilingual-fake-news

The code related to the paper

m3m

meker

ACL SRW

multilingual_detox

ACL SRW "Exploring cross-lingual textual style transfer with large multilingual language models"

pywikidata

Python Wrapper for Wikidata KG

subgraph_kgqa

touche

Code for reproducing of our submission to the CLEF-2020 shared task on argument retrieval.

transformers-course

Materials of transformers lecture course

compression

Project on transformers compression

feedback_generation_nigula

lewit-informal

semantic-role-labelling

SGDD-TST

Dataset for evaluating the quality of content preservation measure in text formality transfer for task oriented domain

act

formality

formality

isotropy

Code related to the paper on isotropy of CLIP embeddings

konstruktor

Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering

MNAS_Demo

mt0-detox

A code for PAN-2024 Multilingual Text Detoxification

multilingual_news_similarity

Repo for code and experiments track for SemEval 2022 Task 8: Multilingual News Article Similarity

s3

S3: A Simple Strong Sample-effective Multimodal Dialog System

shroom

SHROOM SemEval shared task code and data

taxgen-demo

Demo for https://github.com/skoltech-nlp/taxgen

wikidata-simplequestions-hf

Huggingface dataset for wikidata-simplequestions

wikidata_rubq

HF wikidata RuBQ2