Natural Language Processing news and analysis on Web Pulse: 5520 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
The Guardian's Football Weekly podcast revealed that artificial intelligence is reshaping football scouting, transfer gossip, and tactical analysis, with clubs increasingly relying on machine learning models for recruitm…
Microsoft has introduced SharePoint Skills, a feature that lets users create reusable, multi-step AI workflows within SharePoint using natural language. The tool, managed via the site's Agent Assets library, automates re…
FunASR, an industrial-grade speech recognition toolkit, released an update in August 2026, achieving up to 340x realtime speed and 26x faster than Whisper, supporting 50+ languages, speaker diarization, emotion detection…
A team from ZeroR achieved 2nd place on hate speech detection (F1: 0.797) and 4th place on sentiment analysis (F1: 0.518) in the CHiPSAL 2026 shared task on multimodal hate speech and sentiment detection in Nepali memes,…
A new inference-time framework, Adjudicated Captioning, achieves CIDEr 117.6 and SPICE 21.9 on the COCO Karpathy test split for zero-shot image captioning, up from 108.0 and 20.3 for the baseline IFCap, a +9.6 CIDEr gain…
Researchers propose a new unsupervised data augmentation method combining Gaussian Mixture Models (GMMs) and Large Language Models (LLMs) to improve clustering of underrepresented topics in imbalanced text datasets. The …
A study on arXiv (2607.28634v1) found that zero-shot GPT-4.1 with a temperature of 0 achieved the highest item difficulty prediction accuracy among large language models, with a quadratic weighted kappa (QWK) of 0.578, b…
Researchers introduced Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts to improve downstream LLM performance, trained via reinforcement learning with Group Relative P…
Researchers introduced TELLER, a dual-path iterative preference optimization method for table entity linking, which improves accuracy on the TableInstruct entity-linking subset from 94.35% to 94.50% via a direct-answer p…
The AI Visibility Checker, launched on aivisibility.pro, lets brands see whether ChatGPT, Gemini, Claude, and Perplexity recommend them in response to real customer prompts, providing a free AI visibility score and per-p…
A developer released claude-real-video, an open-source tool that lets AI agents like Claude Desktop and Cursor watch videos by extracting scene-aware keyframes and timestamped transcripts locally. The tool, available as …
A developer has created a tool to score the semantic density of MCP tool descriptions, arguing that verbose, human-friendly descriptions cause LLM agents to hallucinate and fail. The tool, available at vinkius.com, analy…
Adobe is hiring a Machine Learning Engineer in Bangalore to build and train models for creative understanding across vision, video, and language, supporting its Content Intelligence group. The role requires a Master's de…
A developer built a RAG system over 62 ancient-history books (~46,000 chunks) and measured retrieval techniques against a fixed 161-question test set. The production system ships without hybrid search or reranking, as th…
A developer's RAG system built on six podcast episodes incorrectly answered that Marcus Chen leads the team responsible for the biggest outage, when the correct answer was Priya Raman, because the retrieved chunks never …
A developer is building SoulFix, an AI image editor that uses a CNN-RNN architecture to interpret user intent from scribbles, and Friday, a self-aware assistant with sentiment analysis and entity recognition. The develop…
Microsoft is testing a new native real-time voice model, MAI Realtime, which has appeared as a hidden early-access entry in its MAI Playground. The bidirectional, full-duplex system, which listens and speaks simultaneous…
Crest, a new Mac app, functions as a notch-based control room that can answer Claude Code prompts, record meetings, and manage notes locally. The app integrates with macOS models to transcribe and summarize calls, with a…
A developer argues that threshold-based voice activity detection for turn-taking in voice agents is fundamentally flawed, as raising the silence threshold trades interruptions for perceived slowness. They propose an alte…
TamedTable, a source-available AI ETL tool, lets users transform tabular data using natural language instead of formulas or code, and its benchmark shows the default model matched hand-checked labels 96.7% of the time at…