Romanian
PulseAugur coverage of Romanian — every cluster mentioning Romanian across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
Cathay Pacific flight intercepted by NATO jets due to crew radio frequency error
A Cathay Pacific flight from Hong Kong to London was intercepted by Hungarian fighter jets over Romania due to a communication error. The flight crew mistakenly selected the wrong radio frequency while responding to ins…
-
New pipeline tackles gender bias in English-Romanian machine translation
Researchers have developed a novel pipeline to address gender bias in English-to-Romanian machine translation. Their method employs a fine-tuned large language model to identify gender in English sentences and insert ge…
-
New method tackles gender bias in English-Romanian machine translation
Researchers have developed a new method to reduce gender bias in English-to-Romanian machine translation. The approach uses a large language model to classify gender in English sentences and inserts gender hint tags, wh…
-
Open models advance English-Romanian literary translation with new framework
Researchers have developed the TinyFabulist Translation Framework (TF2) to address the challenge of literary translation for low-resource languages like Romanian using open-source models. The framework utilizes a large …
-
New lightweight method for Romanian text authorship attribution unveiled
Researchers have developed CHiPS, a novel, lightweight method for attributing authorship of Romanian texts based on character-level analysis. This method utilizes character histograms and positional signals, avoiding co…
-
New Romanian Lexical Simplification Dataset and System Introduced
Researchers have introduced RALS, the first dataset designed for both lexical complexity prediction and lexical simplification specifically for the Romanian language. This dataset includes human annotations for lexical …
-
New Romanian Visual Speech Recognition Dataset VSRo-200 Released
Researchers have introduced VSRo-200, a new large-scale dataset for visual speech recognition in Romanian. The dataset includes 200 hours of real-world podcast videos, with a portion annotated by humans and the rest by …
-
Small LLMs rival frontier models in relation extraction tasks
A new research paper explores the effectiveness of large language models (LLMs) for cross-lingual relation extraction, specifically focusing on Romanian. The study found that while LLMs like Gemma 4 31B show a performan…
-
New Romanian speech corpus tackles demographic bias in parliamentary ASR
Researchers have developed a new dataset and framework for improving Romanian-accented speech recognition, specifically for parliamentary proceedings. The ROManian PARliamentary Speech Corpus (ROMPAR) includes 17.80 hou…
-
MAVEN framework improves cultural fidelity in text-to-video generation
Researchers have developed MAVEN, a multi-agent framework aimed at enhancing the cultural accuracy of text-to-video generation. This system breaks down prompts into distinct components like person, action, and location,…
-
New dataset RoIt-XMASA aids Romanian and Italian sentiment analysis
Researchers have introduced RoIt-XMASA, a new dataset designed for multilingual sentiment analysis in Romanian and Italian. This dataset includes 36,000 labeled reviews across books, movies, and music, along with over 2…
-
Romanian GEC corpus and Transformer models introduced
Researchers have developed a new dataset and neural models for Grammatical Error Correction (GEC) specifically for the Romanian language. This effort addresses the scarcity of resources for GEC in non-English languages,…