Papers with Russian
Negation typology and general representation models for cross-lingual zero-shot negation scope resolution in Russian, French, and Spanish. (2021.naacl-srw)
Copied to clipboard
| Challenge: | Negation resolution remains an acute and continuously researched question in Natural Language Processing. |
| Approach: | They propose to use multilingual pre-trained general representation models to detect negation scope in languages without annotated data. |
| Outcome: | The proposed model achieves token-level F1 score between English, Spanish, French, and Russian. |
GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture (2025.acl-demo)
Copied to clipboard
Valentin Mamedov, Evgenii Kosarev, Gregory Leleytner, Ilya Shchuckin, Valeriy Berezovskiy, Daniil Smirnov, Dmitry Kozlov, Sergei Averkiev, Lukyanenko Ivan, Aleksandr Proshunin, Ainur Israfilova, Ivan Baskov, Artem Chervyakov, Emil Shakirov, Mikhail Kolesov, Daria Khomich, Daria Latortseva, Sergei Porkhun, Yury Fedorov, Oleg Kutuzov, Polina Kudriavtseva, Sofiia Soldatova, Kolodin Egor, Stanislav Pyatkin, Dzmitry Menshykh, Grafov Sergei IUrevich, Eldar Damirov, Vladimir Karlov, Ruslan Gaitukiev, Arkadiy Shatenov, Alena Fenogenova, Nikita Savushkin, Fedor Minkin
| Challenge: | generative large language models have become crucial for modern NLP research and applications across multiple languages. |
| Approach: | They introduce the GigaChat family of Russian LLMs, available in various sizes . they evaluate their performance on Russian and English benchmarks and compare them with multilingual analogs . |
| Outcome: | The proposed model family is available in various sizes and is tested on Russian and English benchmarks. |
MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages (2023.findings-eacl)
Copied to clipboard
| Challenge: | MCoNaLa benchmarks natural language code generation in languages that are not native to English. |
| Approach: | They propose to benchmark natural language code generation from natural language commands extending beyond English by using a multilingual dataset. |
| Outcome: | The proposed dataset compares natural language commands with code generation systems in three languages. |
MultiMUC: Multilingual Template Filling on MUC-4 (2024.eacl-long)
Copied to clipboard
William Gantt, Shabnam Behzad, Hannah An, Yunmo Chen, Aaron White, Benjamin Van Durme, Mahsa Yarmohammadi
| Challenge: | We present multilingual parallel template filling datasets for MUCs . systems were required to extract one template per incident, containing details about perpetrators, victims, weapons used . |
| Approach: | They introduce MultiMUC, the first multilingual parallel corpus for template filling . they obtain automatic translations from a strong multilingual machine translation system . |
| Outcome: | The proposed dataset includes translations of the classic MUC-4 template filling benchmark into Arabic, Chinese, Farsi, Korean, and Russian. |
Using Morphological Knowledge in Open-Vocabulary Neural Language Models (N18-1)
Copied to clipboard
| Challenge: | Existing models that generate words from a fixed vocabulary are linguistically nave . authors present an open-vocabulary language model that incorporates morphological knowledge into a neural framework . |
| Approach: | They propose a model that incorporates morphological knowledge into a neural model by generating words as a sequence of characters, generating full word forms and combining them with a hand-written morphology analyzer. |
| Outcome: | The proposed model outperforms character-based models on Finnish, Turkish, and Russian on three languages. |
Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias (2020.emnlp-main)
Copied to clipboard
| Challenge: | English challenge datasets highlight gender-ambiguous occurrences of ‘doctor’ as male doctors, but they are not useful for other languages. |
| Approach: | They propose to build multi-task challenge datasets for detecting gender bias that lead to unambiguously wrong model predictions for languages with type B reflexivization. |
| Outcome: | The proposed dataset can detect gender bias in languages with type B reflexivization and spans four languages and four NLP tasks. |
How Good (really) are Grammatical Error Correction Systems? (2021.eacl-main)
Copied to clipboard
| Challenge: | Standard evaluations of Grammatical Error Correction systems use a fixed reference text generated relative to the original text. |
| Approach: | They propose to use a gold reference text to evaluate Grammatical Error Correction systems that is generated relative to the original text and is independent of the system output. |
| Outcome: | The proposed evaluations show that the system performs 20-40 points better than standard evaluations. |
Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog (2022.naacl-main)
Copied to clipboard
| Challenge: | Task-oriented dialog (TOD) is arguably one of the most popular natural language processing (NLP) application areas. |
| Approach: | They propose a multilingual multi-domain TOD dataset that spans four languages . they use a framework for multilingual conversational specialization of pretrained language models . |
| Outcome: | The proposed datasets show that they perform better than existing datasets in English . the proposed framework allows for sample-efficient few-shot transfer for TOD tasks . |
MGAD: Multilingual Generation of Analogy Datasets (L18-1)
Copied to clipboard
| Challenge: | Existing methods for word embedding evaluation are computationally expensive and task-specific. |
| Approach: | They propose a minimally supervised method for generating word embedding evaluation datasets for a large number of languages using existing dependency treebanks and parsers. |
| Outcome: | The proposed method evaluates three popular word embedding algorithms against these datasets and shows that their performance varies between syntactic categories. |
Constructing Korean Learners’ L2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual L2 speech corpora for automatic speech assessment are currently available, but lack comprehensive annotations of L2 from non-native speakers of various languages. |
| Approach: | They propose to use Korean learners’ L2 speech corpus of seven languages to develop automatic speech assessment. |
| Outcome: | The proposed corpus contains 1,200 hours of L2 speech data from Korean learners (400 hours for English, 200 hours each for Japanese and Chinese, 100 hours each in French, German, Spanish, and Russian). |
BERT-like Models for Slavic Morpheme Segmentation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing morpheme segmentation algorithms for Slavic languages have been improved but performance is still low for words with roots not present in training data. |
| Approach: | They propose to fine-tune BERT-like models for morpheme segmentation using data from Belarusian, Czech, and Russian to account for word semantics. |
| Outcome: | The proposed models outperform all previous approaches in Czech and Russian, with word-level accuracy of 92.5-95.1%. |
Croatian Idioms Integration: Enhancing the LIdioms Multilingual Linked Idioms Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets that include idioms from English, German, Italian, Portuguese and Russian do not include a comprehensive representation of idiomatic expressions in Croatian. |
| Approach: | They propose to extend existing RDF-based multilingual representation of idioms to include 1,042 Croatian idiomes in an Ontolex Lemon format. |
| Outcome: | The proposed resource includes 1,042 Croatian idioms in an Ontolex Lemon format to foster translation initiatives and facilitate intercultural exchange. |
LIdioms: A Multilingual Linked Idioms Data Set (L18-1)
Copied to clipboard
| Challenge: | Recent studies have focused on linguistic data sets that are bilingual on the Linguistic Linked Open Data (LLOD) 1 . |
| Approach: | They describe a multilingual RDF representation of idioms currently containing five languages . they use a model to structure the data and a method to link the data to well-known multilingual data sets such as BabelNet. |
| Outcome: | The proposed model complies with best practices according to Linguistic Linked Open Data Community. |
The Morpho-syntactic Annotation of Animacy for a Dependency Parser (L18-1)
Copied to clipboard
| Challenge: | Animacy is a feature found in nouns such as 'gender', 'number' and 'case' that improves parser accuracy. |
| Approach: | They propose an annotation scheme and parser results for the animacy feature in Russian and Arabic, morphologically rich languages, using the universal dependency framework. |
| Outcome: | The proposed scheme and parser improve on the animacy feature in Russian and Arabic, and the results show that the feature is more accurate than other features found in nouns, namely, 'gender', , and 'number' |
Multilingual Nonce Dependency Treebanks: Understanding how Language Models Represent and Process Syntactic Structure (2024.naacl-long)
Copied to clipboard
| Challenge: | a number of studies have focused on making explicit the linguistic information encoded in language models (LMs) however, this method has been criticized for various reasons. |
| Approach: | They introduce a framework for creating nonce treebanks for multilingual UD corpora . they investigate word co-occurrence statistics and show how nonce data affects the performance of syntactic dependency probes. |
| Outcome: | The proposed framework satisfies syntactic argument structure and ensures grammaticality via language-specific rules. |
Non-autoregressive Text Editing with Copy-aware Latent Alignments (2023.emnlp-main)
Copied to clipboard
| Challenge: | Seq2Edit approaches still face several challenges such as inflexibility in generation and difficulty in generalizing to other languages. |
| Approach: | They propose a non-autoregressive text editing method that models the edit process with latent CTC alignments and introduces the copy operation into the edit space. |
| Outcome: | The proposed method outperforms existing Seq2Edit models and achieves similar or even better results than Seq1Edit with over 4 speedup. |
Stereotype Bias in a Bilingual Setting: A Culturally Grounded Evaluation in Kazakhstan (2026.acl-long)
Copied to clipboard
Nurkhan Laiyk, Daniil Orel, Ayana Mussabayeva, Maiya Goloburda, Kamila Kuishibekova, Liya Goloburda, Diana Turmakhan, Preslav Nakov, Yuxia Wang, Fajri Koto
| Challenge: | Stereotype bias in language models is largely understudied in English . language models perform strongly on downstream NLP tasks, but they are pre-trained on large text corpora . |
| Approach: | They use a dataset to assess stereotype bias in language models in Kazakhstan . they find that stereotype bias is most pronounced in code-mixed inputs . |
| Outcome: | The proposed dataset shows that stereotype bias is most pronounced in code-mixed inputs. |
Baselines and Test Data for Cross-Lingual Inference (L18-1)
Copied to clipboard
| Challenge: | Recent research on textual entailment is limited to English, but it is expanding to other languages. |
| Approach: | They propose to extend the research in SNLI-style natural language inference toward multilingual evaluation by using cross-lingual word embeddings and machine translation. |
| Outcome: | The proposed system scores an average accuracy of just over 75%, but it is not perfect. |
MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have shown remarkable capabilities in open information extraction, but their resource requirements often restrict their deployment in resource-constrained industrial settings. |
| Approach: | They introduce an ultra-lightweight large language model trained on instruction-based samples in Chinese, English, Korean, and Russian. |
| Outcome: | The proposed model outperforms large-scale models with up to 70B parameters, reducing computational resources by 140x and delivering 11x faster response times. |
Multilingual Generation and Answering of Questions from Texts and Knowledge Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for QG-QA are limited to English, but can be used in other languages. |
| Approach: | They propose to bring multilinguality to multimodal QG-QA by using Brazilian Portuguese and Russian data. |
| Outcome: | The proposed approach outperforms a baseline on English and can handle both languages. |
Multimodal and Multilingual Laughter Detection in Stand-Up Comedy Videos (2024.lrec-main)
Copied to clipboard
| Challenge: | Using TED talks, we use laughter detection software to capture humor in the sitcom genre. |
| Approach: | They develop a multimodal multilingual dataset in Russian and English with a particular emphasis on laughter detection techniques. |
| Outcome: | The proposed model outperforms peak detection and machine learning, while the latter shows promise and warrants further study. |
The Linearity of the Effect of Surprisal on Reading Times across Languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a large amount of insight into human language processing can be gleaned by studying word-by-word processing difficulty. |
| Approach: | They extend the study by examining eyetracking corpora of seven languages . they find evidence for superlinearity in some languages, but highly sensitive to language models . |
| Outcome: | The study extends existing studies on english to Danish, Dutch, English, German, Japanese, Mandarin, and Russian. |
NarratEX Dataset: Explaining the Dominant Narratives in News Texts (2025.findings-emnlp)
Copied to clipboard
Nuno Guimarães, Purificação Silvano, Ricardo Campos, Alipio Jorge, Ana Filipa Pacheco, Dimitar Iliyanov Dimitrov, Nikolaos Nikolaidis, Roman Yangarber, Elisa Sartori, Nicolas Stefanovitch, Preslav Nakov, Jakub Piskorski, Giovanni Da San Martino
| Challenge: | a dataset is created to explain the choice of the dominant narrative in a news article . the dataset is intended to address discourse polarization and propaganda detection . |
| Approach: | They propose a dataset for explaining the choice of the dominant narrative in a news article . the dataset is annotated manually with a dominant narrative and sub-narrative labels . |
| Outcome: | The proposed dataset is designed to explain the choice of the dominant narrative in a news article. |
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST) (2025.findings-acl)
Copied to clipboard
Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona T. Diab
| Challenge: | Despite advances in machine translation, domain-specific terminology translation remains challenging. |
| Approach: | They propose a large-scale multilingual AI terminology dataset that combines LLMs for extraction with human expertise for translation. |
| Outcome: | The proposed framework combines human translation expertise with LLMs to improve translation accuracy and improve BLEU and COMET scores. |
Explaining novel senses using definition generation with open language models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | We apply definition generators based on open-weights large language models to create explanations of novel senses. |
| Approach: | They apply open-weights large language models to create explanations of novel senses using target word usages as input. |
| Outcome: | The proposed definition generators perform on par with decoder-only models. |
Can AI-Generated Persuasion Be Detected? Persuaficial Benchmark and AI vs. Human Linguistic Differences (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate highly persuasive text, raising concerns about misuse for propaganda, manipulation, and other harmful purposes. |
| Approach: | They propose a multilingual benchmark to compare LLM-generated persuasive texts with human-written ones. |
| Outcome: | The proposed benchmark compares human-authored and LLM-generated persuasive texts . it finds that overtly persuasive LLMs are easier to detect than human-written ones . |