Vietnamese
PulseAugur coverage of Vietnamese — every cluster mentioning Vietnamese across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
AI drama tools: 5 questions to ask before buying
The article outlines five key questions for evaluating AI tools designed for creating vertical short dramas, emphasizing character consistency across episodes. It highlights the importance of saved character references,…
-
New benchmark PhoPunct evaluates Transformer architectures for Vietnamese punctuation restoration
Researchers have developed PhoPunct, a large-scale benchmark for evaluating Vietnamese punctuation restoration models. The benchmark, comprising 22.1 million labeled tokens from News and Novels corpora, was used to test…
-
Siri AI adds four new languages in iOS 27.3 beta
Siri AI is expanding its language support with the beta release of iOS 27.3, adding Traditional Chinese, Norwegian, Turkish, and Vietnamese. This follows a rapid expansion just a week prior, when iOS 27.2 introduced Fre…
-
Multilingual LLMs show shared negation representations across languages
Researchers have investigated how multilingual large language models (LLMs) represent negation across different languages. Their study, using causal interventions on synthetic and translation datasets, found that these …
-
Vietnamese text classification models show varied performance, sensitivity to diacritics
A new study on arXiv investigates the effectiveness of specialized decision models for text classification in Vietnamese. The research evaluated four models across 13 classification settings, testing zero-shot performan…
-
GoiBERT: Compact Vietnamese Language Models Achieve High Performance
Researchers have developed GoiBERT, a new family of compact Vietnamese language models designed for efficient deployment. These models, with 26M and 49M parameters, achieve strong performance across various benchmarks, …
-
VietMed dataset released for Vietnamese medical ASR
Researchers have introduced VietMed, a substantial new dataset and benchmark for Vietnamese medical Automatic Speech Recognition (ASR). This dataset is reportedly the largest of its kind globally, featuring 16 hours of …
-
Solo dev uses Groq LLM API for 8-language website translation
A solo developer in South Korea has implemented an 8-language interface for their browser game hub, Yeoul Games, using Python and Docker. The system automatically translates game descriptions via the Groq LLM API, with …
-
New end-to-end ITN system achieves real-time processing with language model
Researchers have developed a new end-to-end system for Inverse Text Normalization (ITN) that can process speech recognition outputs in real-time. This system adapts a pretrained text-to-text language model and employs a…
-
New research tackles OCR errors with character verification and severity-weighted metrics · 4 sources tracked
Two new research papers address challenges in optical character recognition (OCR). The first introduces a Character Verification Model (CVM) to correct visually similar characters like 'O'/'0' and 'S'/'5', improving acc…
-
Hong Kong police arrest 127 in Vietnamese loan-sharking syndicate bust
Hong Kong police have arrested 127 individuals in connection with a six-month operation targeting a Vietnamese-led loan-sharking syndicate. The group is accused of charging exorbitant daily interest rates, reportedly HK…
-
YupVox launches AI text-to-speech with 3 Vietnamese accents
YupVox has launched a new AI-powered text-to-speech service that can generate Vietnamese speech in three distinct regional accents: Northern, Central, and Southern. The tool allows users to select their preferred accent…
-
Keystroke analysis struggles to detect LLM-assisted Vietnamese writing
Researchers have developed a method to detect writing assisted by large language models (LLMs) using keystroke dynamics, particularly for Vietnamese text. Their study introduced a dataset capturing various writing modes…
-
YupVox Converts Books to Audiobooks Using AI for Vietnamese Authors
YupVox is a tool designed to convert physical books into professional audiobooks, particularly for the Vietnamese market. The service aims to assist Vietnamese authors by leveraging advanced AI for voice generation and …
-
New ViLegalExpert benchmark targets Vietnamese Legal AI challenges
Researchers have introduced ViLegalExpert, a new large-scale benchmark designed to improve Vietnamese Legal AI. This benchmark is built from over 172,000 real-world citizen-lawyer consultations, covering 34 legal domain…
-
New framework diagnoses TTS failures in complex multilingual text
Researchers have developed a new framework to evaluate the robustness of low-resource multilingual text-to-speech (TTS) systems when processing complex text inputs. This framework assesses content consistency, language …
-
Japan hikes foreign worker fees, permanent residency requirements
Japan is increasing fees for residence permits and permanent residency applications, alongside stricter requirements for the latter. These changes come as the nation becomes more reliant on foreign labor to combat its s…
-
AI-generated explicit manga content shared on Mastodon · 10 sources tracked
This cluster consists of multiple posts from Mastodon user @no_inheritance, all tagged with #AI, #manga, and #cartoon. The posts also contain explicit content and tags related to nudity and various body parts, alongside…
-
New En-ViMedNER corpus aids Vietnamese biomedical NLP research
Researchers have introduced En-ViMedNER, the first parallel English-Vietnamese biomedical Named Entity Recognition (NER) corpus. This corpus is annotated with Unified Medical Language System (UMLS) semantic types, provi…
-
Seoul district expands multilingual rental aid for foreign residents
The Gangbuk district in Seoul, South Korea, is enhancing its program to assist foreign residents with the rental market. This initiative provides multilingual administrative guidance in nine languages for essential hous…