Natural Language Processing news and analysis on Web Pulse: 5440 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Iris-pro, a 397B parameter search agent developed by an open-source research team, achieved a 92.9 accuracy score on the DeepSearchQA benchmark with context management enabled, setting a new state-of-the-art result for o…
A developer has released a large Word2Vec model trained on 13 billion words of Russian fiction, available on Hugging Face under the MIT license. The lemma-based CBOW model with 300-dimensional vectors captures literary s…
A developer building an automated subtitle pipeline for AI-generated ad videos discovered that their caption timing validation was flawed. The developer found that a ratio-based guard, which rejected clips where a single…
Researchers developed VERGE, an agentic workflow using retrieval-augmented generation and a bounded verification-refinement cycle, to extract red-flag symptoms and family-history risk status for early-onset colorectal ca…
A new benchmark for evaluating large language models' social pragmatic inference on Chinese online comments shows that the strongest model, GPT-4, achieves 81.42% leave-writer-out accuracy, while the mean across eight mo…
Researchers introduced LentEx, a framework for latent entity extraction that uses synthetic data generation and instruction-tuned large language models, claiming it is the first to systematically address this task with L…
A new arXiv study (2609.04409v1) systematically evaluated cross-lingual consistency (CLC) enhancement methods in multilingual language models, finding that post-training methods, especially direct distribution alignment,…
The Fort That Holds, represented by a bot named River, released F.I.N.E., an MIT-licensed framework for interpreting nonliteral expression. The tool analyzes unstructured emotional text and converts it into useful artifa…
Microsoft AI released MAI-Transcribe-2 on September 3 at $0.10 per audio hour, claiming it is 72% cheaper than OpenAI's GPT-Transcribe and 10x faster in non-streaming tests, with a 5.2% average word error rate on the FLE…
An AI developer using a VOICEVOX-compatible text-to-speech engine found that its pitch-recalculation endpoints returned 0.0 for all mora values, because the engine is end-to-end neural and does not expose per-mora pitch …
Nyra Labs released CrisperWhisper 2.0, a multilingual speech-to-text model that transcribes speech verbatim or as intended, with word-level timings averaging 30 ms boundary error on read speech and 41 ms on conversationa…
Meta released Muse Voice Transcribe on September 1, 2026, and Microsoft released MAI-Transcribe-2 on September 3, 2026, with Meta reporting first place on the Artificial Analysis streaming STT ranking and Microsoft repor…
ElevenLabs and Murf AI lead a fragmented market of 21 AI text-to-speech tools, with ElevenLabs offering voice cloning from one minute of audio and multilingual dubbing across 24 languages, priced from free to $990 per mo…
Midea's new Smart Master appliances use AI agents and natural language voice commands to control home devices without a remote or phone, as reported by Forbes contributor Prakhar Khanna.
Meta's Superintelligence Labs released Muse Voice Transcribe, a real-time transcription model that processes speech in 80-millisecond chunks, distinguishes speakers, and detects sentence boundaries. According to Artifici…
Twilio unveiled its Conversational AI suite at SIGNAL 2026, including the Conversation Orchestrator, Conversation Memory, Conversation Intelligence, Agent Connect, and Enterprise Knowledge API, alongside reported Q2 reve…
A developer published a strict prose-editing prompt designed to strip recognizable Claude/LLM writing tics from documents while preserving facts, technical meaning, and the author's intended confidence level. The prompt …
Companies migrating from legacy IVR to AI voice agents cut average handle time by 30–50%, raise self-service rates from under 25% to as high as 70%, and reduce misrouting from 30% to below 10%, according to a migration p…
Toronto-based cloud, AI, and DevOps company Dedicatted reports that its bilingual AI shopping assistant for Kuwaiti e-commerce platform Taw9eel lifted average order value by six percent, sped up product discovery, and im…
A local embedding model, a second smaller model that converts text into vectors, is essential for retrieval-augmented generation (RAG) setups, as it retrieves relevant document chunks for the LLM. According to a plain-En…