Papers with Romanian
Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources (2022.lrec-1)
Copied to clipboard
Tamás Váradi, Bence Nyéki, Svetla Koeva, Marko Tadić, Vanja Štefanec, Maciej Ogrodniczuk, Bartłomiej Nitoń, Piotr Pęzik, Verginica Barbu Mititelu, Elena Irimia, Maria Mitrofan, Dan Tufiș, Radovan Garabík, Simon Krek, Andraž Repar
| Challenge: | The CURLICAT CEF Telecom project aims to collect and deeply annotate a set of large corpora from selected domains. |
| Approach: | They present the results of the CURLICAT CEF Telecom project . they propose to collect and deeply annotate a set of large corpora from selected domains . |
| Outcome: | The CURLICAT CEF Telecom project provides a set of large corpora from selected domains . the corporatized corporates are tokenized, lemmatized and morphologically analysed . |
A Lifelong Multilingual Multi-granularity Semantic Alignment Approach via Maximum Co-occurrence Probability (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to mask and predict tokens in multilingual text limit multilingual interaction . |
| Approach: | They propose a lifelong multilingual multi-granularity semantic alignment approach which continuously extracts massive aligned linguistic units from noisy data via a maximum co-occurrence probability algorithm. |
| Outcome: | The proposed approach improves translation performance on WMT14 18 benchmarks in twelve directions. |
A Multilingual Parallel Corpus for Aromanian (2024.lrec-main)
Copied to clipboard
| Challenge: | Aromanian is an endangered 1 language that currently lacks corpora and electronic resources that can potentially contribute to the preservation of its cultural heritage. |
| Approach: | They propose to create a corpus of Aromanian and equivalent sentence-aligned translations into Romanian, English, and French using orthographic standards. |
| Outcome: | The authors report that the first high-quality corpus of Aromanian is available in the Balkans and is available for download in Romanian, English, and French. |
Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa - A Large Romanian Sentiment Data Set (2021.eacl-main)
Copied to clipboard
| Challenge: | Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools. |
| Approach: | They introduce a Large Romanian Sentiment Data Set which is composed of 15,000 positive and negative reviews collected from the largest Romanian e-commerce platform. |
| Outcome: | The proposed data set is composed of 15,000 positive and negative reviews from the largest Romanian e-commerce platform. |
The Reference Corpus of the Contemporary Romanian Language (CoRoLa) (L18-1)
Copied to clipboard
| Challenge: | a four-year project focused on the creation of a big corpus for contemporary Romanian language is underway . the corpus is the largest publicly available corpus of contemporary Romania . |
| Approach: | a four-year project is focusing on the creation of a big corpus for Romanian language . the corpus is the largest publicly available corpus of the language based in the country . authors propose to use the corpora as a tool to query and listen to the results . |
| Outcome: | a four-year project has created the largest publicly available corpus of Romanian language . the corpus is the result of a project focused on the creation of 'corola.racai.ro' the written component contains 1,257,752,812 tokens, distributed in several languages . |
Automatic Discrimination between Inherited and Borrowed Latin Words in Romance Languages (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to discriminate between inherited and borrowed Latin words have been used to investigate the problem of automatic discrimination between a language's sound shifts. |
| Approach: | They propose a new dataset to investigate the problem of automatically discriminating between inherited and borrowed Latin words in Romance languages. |
| Outcome: | The proposed model can automatically discriminate between inherited and borrowed Latin words on two versions of the dataset, orthographic and phonetic. |
Ensemble Romanian Dependency Parsing with Neural Networks (L18-1)
Copied to clipboard
| Challenge: | SSPR is a Python 3.5 application based on the Microsoft Cognitive Toolkit 2.0 Python API. |
| Approach: | a Python 3.5 application is based on the Microsoft Cognitive Toolkit 2.0 Python API. |
| Outcome: | SSPR outperforms the best individual parser at the CONLL 2017 dependency parsing shared task. |
RoQLlama: A Lightweight Romanian Adapted Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, open-source large language models are limited to tasks involving the English language. |
| Approach: | They propose to use QLoRA to train a Romanian-adapted LLM with 7 billion parameters and quantized to 4 bits to improve model's performance. |
| Outcome: | The proposed model outperforms the other LLMs on four out of the seven tasks investigated using zero-shot prompting. |
Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Empirical results on machine translation suggest that DPE is effective for segmenting output sentences. |
| Approach: | They propose a new algorithm for tokenizing sentences into subword units . they propose enabling exact log marginal likelihood estimation and exact MAP inference . |
| Outcome: | The proposed algorithm improves on machine translation datasets and on a large dataset. |
ISO-based Annotated Multilingual Parallel Corpus for Discourse Markers (2022.lrec-1)
Copied to clipboard
Purificação Silvano, Mariana Damova, Giedrė Valūnaitė Oleškevičienė, Chaya Liebeskind, Christian Chiarcos, Dimitar Trajanov, Ciprian-Octavian Truică, Elena-Simona Apostol, Anna Baczkowska
| Challenge: | Discourse markers carry information about the discourse structure and organization, and also signal local dependencies or epistemic stance of speaker. |
| Approach: | They propose an ISO-based annotated multilingual parallel corpus for discourse markers . they propose an annotation scheme for discourse relations with a plug-in to ISO 24617-2 . |
| Outcome: | The proposed language resource is based on an ISO-based annotated multilingual parallel corpus of discourse markers. |
RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams (2026.findings-eacl)
Copied to clipboard
Andrei Vlad Man, Răzvan-Alexandru Smădu, Cristian-George Craciun, Dumitru-Clementin Cercel, Florin Pop, Mihaela-Claudia Cercel
| Challenge: | a growing need for tools that support legal education, especially in under-resourced languages such as Romanian . we evaluate the capabilities of large language models and vision-language models in legal education . |
| Approach: | They evaluate the capabilities of Large Language Models and Vision-Language Models in Romanian driving law through textual and visual question-answering tasks. |
| Outcome: | The proposed model improves retrieval performance and QA accuracy in Romanian driving tests. |
A Computational Exploration of Pejorative Language in Social Media (2021.findings-emnlp)
Copied to clipboard
| Challenge: | In this paper, we examine the problem of pejorative language, an under-explored topic in computational linguistics. |
| Approach: | They propose to automatically disambiguate pejorative usage in social media . they leverage online dictionaries to build a multilingual lexicon of pejorativ terms . |
| Outcome: | The proposed model can automatically disambiguate pejorative usage in social media posts . the proposed model is based on dictionaries and tweets . |
When Do Language Models Endorse Limitations on Human Rights Principles? (2026.findings-eacl)
Copied to clipboard
Keenan Samway, Miu Nicole Takagi, Rada Mihalcea, Bernhard Schölkopf, Ilias Chalkidis, Daniel Hershcovich, Zhijing Jin
| Challenge: | a recent study evaluated how large language models navigate trade-offs involving the Universal Declaration of Human Rights. |
| Approach: | They evaluate how large language models navigate trade-offs involving the Universal Declaration of Human Rights (UDHR) they use 1,152 synthetically generated scenarios across 24 rights articles and eight languages . |
| Outcome: | The proposed models accept limiting economic, social, and cultural rights more often than political and civil rights, the authors show . their models show significant cross-linguistic variation with elevated endorsement rates of rights-limiting actions in Chinese and Hindi compared to English or Romanian . |
Extracting Linguistic Knowledge from Speech: A Study of Stop Realization in 5 Romance Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | voicing alternation phenomena of stops are a common problem in connected speech . phoneticians and phonologists are interested in analyzing phonetic variation . |
| Approach: | They use forced alignment with pronunciation variants and machine learning techniques to examine voicing alternations of stops in Romance languages. |
| Outcome: | The proposed method enables linguists to use large corpora and speech recognition systems . the results show that voicing alternations occur in all Romance languages . |
Neural Transduction for Multilingual Lexical Translation (2020.coling-main)
Copied to clipboard
| Challenge: | a method for completing multilingual translation dictionaries is proposed . a 27% relative improvement in whole-word accuracy is achieved when multilingual data is unavailable . |
| Approach: | They propose a method for completing multilingual translation dictionaries using multilingual inputs and multilingual decoding objective. |
| Outcome: | The proposed method can synthesize new word forms in multilingual translation dictionaries . it can perform in settings where correct translations have not been observed in text . |
Resources in Underrepresented Languages: Building a Representative Romanian Corpus (2020.lrec-1)
Copied to clipboard
Ludmila Midrigan - Ciochina, Victoria Boyd, Lucila Sanchez-Ortega, Diana Malancea_Malac, Doina Midrigan, David P. Corina
| Challenge: | Currently, the corpus has approximately 5,500,000 tokens originating from written text and 100,000 tokens of spoken language. |
| Approach: | They describe the process of creating a large and representative corpus in Romanian, a relatively under-resourced language with unique typological characteristics. |
| Outcome: | The proposed corpus contains 5,500,000 tokens originating from written text and 100,000 tokens of spoken language. |
The MARCELL Legislative Corpus (2020.lrec-1)
Copied to clipboard
Tamás Váradi, Svetla Koeva, Martin Yamalov, Marko Tadić, Bálint Sass, Bartłomiej Nitoń, Maciej Ogrodniczuk, Piotr Pęzik, Verginica Barbu Mititelu, Radu Ion, Elena Irimia, Maria Mitrofan, Vasile Păiș, Dan Tufiș, Radovan Garabík, Simon Krek, Andraz Repar, Matjaž Rihtar, Janez Brank
| Challenge: | MARCELL corpus provides a rich and valuable source for further studies and developments in machine learning, cross-lingual terminological data extraction and classification. |
| Approach: | They present the results of the project MARCELL CEF Telecom . they aim to collect and deeply annotate a large comparable corpus of legal documents . |
| Outcome: | The MARCELL corpus includes 7 monolingual sub-corpora containing the body of respective national legislative documents. |
Investigating the Relationship Between Romanian Financial News and Closing Prices from the Bucharest Stock Exchange (2022.lrec-1)
Copied to clipboard
| Challenge: | a new data set is used to extract information related to one company . a model that is based on previous information about transactions is not enough . |
| Approach: | They use a Romanian financial news website to extract only information related to one company . they use lexicon-based Vader tool, Financial BERT and Transformer-based models . |
| Outcome: | The proposed model shows that the extracted sentiment scores correlate with stock closing prices . the proposed model is based on data from a Romanian financial news website . |
GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Question answering systems have been used for various domains and languages. |
| Approach: | They propose a novel approach for question answering (QA) that combines a dataset of Romanian legal questions with a CROL corpus of laws. |
| Outcome: | The proposed approach achieves competitive results with generally accepted state-of-the-art methods and even exceeds them in most settings. |
“Vorbești Românește?” A Recipe to Train Powerful Romanian LLMs with English Instructions (2024.findings-emnlp)
Copied to clipboard
Mihai Masala, Denis Ilie-Ablachim, Alexandru Dima, Dragos Georgian Corlatescu, Miruna-Andreea Zavelca, Ovio Olaru, Simina-Maria Terian, Andrei Terian, Marius Leordeanu, Horia Velicu, Marius Popescu, Mihai Dascalu, Traian Rebedea
| Challenge: | Large Language Models (LLMs) have achieved almost human-like performance on various tasks. |
| Approach: | They are the first to collect and translate a large collection of texts, instructions, and benchmarks and train, evaluate and release open-source LLMs tailored for Romanian. |
| Outcome: | The proposed model trains, evaluates and releases open-source models tailored for Romanian. |
Aligning the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs (2022.lrec-1)
Copied to clipboard
| Challenge: | Among the language resources for Romanian, there are ones that describe the syntactic and semantic aspects of the language. |
| Approach: | They propose to align two language resources for Romanian: the Romanian Reference Treebank and the Valence Lexicon of Romanian Verbs. |
| Outcome: | The proposed alignments identify morpho-syntactic annotation mistakes, incomplete valence frames or missing ones. |
Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve beam search quality are inadequate in many ways . a new approximation to the beam search curse has been proposed . |
| Approach: | They propose an approximation to minimum Bayes risk decoding that would solve the beam search curse. |
| Outcome: | The proposed approximation has no equivalent to the beam search curse. |
Friend or Foe? A Computational Investigation of Semantic False Friends across Romance Languages (2025.emnlp-main)
Copied to clipboard
| Challenge: | lexical divergence between cognate and borrowings is studied in the five Romance languages. |
| Approach: | They propose to use etymological dictionaries to extract deceptive cognates and borrowings automatically based on usage and freely publish the lexicon of obtained true and deceptives in every Romance language pair. |
| Outcome: | The proposed algorithms are based on the most complete and reliable dataset of cognate words based etymological dictionaries for the five main Romance languages. |
RSC: A Romanian Read Speech Corpus for Automatic Speech Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | Romanian language is under-resourced due to the lack of acoustic and linguistic resources. |
| Approach: | They propose to use a Romanian speech corpus to train automatic speech recognition algorithms based on the spoken hotword detection mechanism. |
| Outcome: | The read speech corpus is a speech recognition system that can perform automatic speech recognition and speech synthesis using state-of-the-art speech recognition toolkit. |
Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing efforts to ensure temporal consistency in large language models are lacking in time-sensitive fields . temporal reasoning is essential for time- sensitive fields such as finance and healthcare . a new benchmark aims to improve temporal referent consistency of LLMs . |
| Approach: | They propose a temporal referential consistency benchmark with a resource TEMP-ReCon to assess LLMs across temporal references. |
| Outcome: | The proposed model improves LLMs' temporal consistency by comparing them to baseline models. |
A Benchmark for Reasoning with Spatial Prepositions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Spatial reasoning is a fundamental building block of human cognition . large language models (LLMs) are not on par with advanced aspects of human cognitive domains . |
| Approach: | They propose a benchmark to assess inferential properties of statements with spatial prepositions . they use prompt engineering to test the performance of two large language models . |
| Outcome: | The proposed benchmark shows that none of the models reaches human performance. |
RoCode: A Dataset for Measuring Code Intelligence from Problem Definitions in Romanian (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models are capable of solving tasks in natural language, but most tests assume they are written in English. |
| Approach: | They propose to use a dataset to measure the generalization power of large language models in a language other than English to evaluate their code intelligence. |
| Outcome: | The proposed dataset provides a benchmark for evaluating the code intelligence of language models trained on Romanian / multilingual text and a fine-tuning set for pretrained Romanian models. |
Towards Building the LEMI Readability Platform for Children’s Literature in the Romanian Language (2024.lrec-main)
Copied to clipboard
Madalina Chitez, Mihai Dascalu, Aura Cristina Udrea, Cosmin Strilețchi, Karla Csürös, Roxana Rogobete, Alexandru Oravițan
| Challenge: | Currently, no existing platform integrates a research-based readability formula for the Romanian language, making this tool unique. |
| Approach: | They propose a new readability tool for children’s literature in the Romanian language that uses a self-compiled corpus and a text analysis interface to generate automatic readability reports for uploaded short texts. |
| Outcome: | The proposed readability tool is specifically targeted at primary school students aged 7-11 . it extracts, tests, and calibrates a readability formula for Romanian using the children’s literature corpus and the platform functionalities. |
RALS: Resources and Baselines for Romanian Automatic Lexical Simplification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text simplification is the process of transforming texts into variants that are simpler to understand by larger audiences or easier to process by existing NLP systems. |
| Approach: | They propose a method for ordering simplification suggestions using a pairwise ranking approximation method, arranging candidates from simple to complex based on a separate set of human judgments. |
| Outcome: | The proposed system is the first to combine lexical simplification and complexity prediction in Romanian with human lexicals. |
Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks suffer from semantic drift and context loss, which can lead to misleading performance metrics. |
| Approach: | They propose a fully automated framework to enable translation of large language models . they propose to use universal self-improvement and multi-round ranking methods to improve translation quality . |
| Outcome: | The proposed framework surpasses existing benchmarks in eight languages and improves translation quality across multilingual domains. |