Natural Language Processing news and analysis on Web Pulse: 3936 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Manticore Search introduced Conversational Search, a feature that combines full-text, vector, and hybrid search with a language model to answer complex product queries, as demonstrated in its Manticore Apparel Shop demo …
Healthwatch Rotherham reported that patients in Yorkshire are struggling to use an AI GP receptionist called EMMA because it cannot understand broad Yorkshire accents, causing frustration and leading some to visit surger…
Google has integrated Gemini Live with its Deep Research capability, enabling users to initiate multi-step research tasks by voice and continue them in the background while switching apps or locking their phones. The upd…
Google DeepMind launched SL2T, a sign-language-to-text model that adds American Sign Language (ASL) dictation to Pixel 11's Gboard and Live Transcribe, while OpenAI introduced GPT-Live, a voice model replacing Advanced V…
Microsoft's GraphRAG system addresses the limitations of standard Retrieval-Augmented Generation (RAG) for global queries that require reasoning across entire document collections, using knowledge graphs and community de…
Conversationaly, a privacy-first AI meeting assistant for macOS, Windows, and Linux, records meetings, transcribes them live, and generates summaries entirely on-device by default, with no account, cloud round-trip, or t…
Sarvam AI's Saaras V3 speech recognition model achieved a word error rate of approximately 19.3% on the IndicVoices top-10 language benchmarks, outperforming OpenAI's GPT-4o Transcribe, ElevenLabs' Scribe v2, Google's Ge…
Google Summer of Code 2026 contributor benchmarking for digiKam's natural language search found that Qwen2.5-1.5B outperformed TinyLlama and a third model on real queries, with Qwen scoring 66% accuracy before label corr…
Hugging Face released Sentence Transformers v6.0, adding a MultiVectorEncoder that natively supports ColBERT-style late interaction and ColPali visual document retrieval checkpoints. The update enables text-to-image docu…
A developer outlines five methods for encoding tacit knowledge into security operations center (SOC) AI agents, emphasizing that the hardest problem is capturing the intuitive judgment of senior analysts. The approaches …
Snowflake's AI_TRANSCRIBE now supports AAC audio, enabling a fully automated call center triage pipeline that transcribes calls, classifies them, and generates summaries without manual note-taking. The demo, created by K…
A developer built a TypeScript coordinator for Tencent RTC voice companions that gives users explicit control over conversational turn-taking, addressing the problem of automatic endpoint detection interrupting users mid…
Researchers introduced SpeechSense, a dataset for fine-grained speech sentiment analysis that defines an 8-class taxonomy of interpersonal stances detectable through prosodic cues, addressing limitations in existing benc…
Researchers at an unnamed institution proposed AISA, a framework using large language models for highway construction safety reporting, achieving 75% held-out accuracy in classifying incidents across OIICS fields. The fr…
Researchers introduced AVShift, the first German benchmark for authorship verification under distribution shifts, comprising over 150,000 text pairs across three genres and 21 years. Experiments showed that fine-tuned LL…
Researchers introduced Dripper, a lightweight framework for main HTML content extraction that uses small language models for constrained sequence labeling, achieving a throughput of 3.08 pages per second on a single A100…
A new arXiv paper (2608.17088v1) proves that the minimum dimensionality required for perfect multilingual embedding spaces grows only logarithmically with the number of languages, showing there is no theoretical curse of…
A new arXiv preprint (arXiv:2608.17218v1) introduces a dataset mapping sentences from 150 novel summaries to their source chapters, finding the task unexpectedly difficult for both human and LLM annotators. The study mea…
Researchers introduced Polaris, a system that trains a large language model to generate table descriptions optimized for retrieval effectiveness using Direct Preference Optimization (DPO) on existing table retrieval benc…
A study from arXiv (2608.17051v1) found that large language models (LLMs) with in-context learning outperform purpose-built de-identification systems in recovering institutionally situated protected health information (P…