Natural Language Processing news and analysis on Web Pulse: 5589 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
A developer built an AI tool that uses embeddings and retrieval-augmented generation to match incident alerts with runbook fixes by meaning rather than keyword overlap, closing the gap between alert messages and document…
A new survey paper on arXiv provides a comprehensive taxonomy of memory systems for AI agents, categorizing memory into forms (token-level, parametric, latent), functions (factual, experiential, working), and dynamics. T…
A developer proposes using AI agents to activate dormant 'weak ties' in professional networks, addressing the gap between having many connections and being able to identify collaboration opportunities. The approach lever…
Opportunity Skill, a new AI agent skill, automatically extracts and maintains a real-time professional interface definition from a user's daily work, eliminating the need for manual profile updates. The skill analyzes re…
Australian universities are using AI detection software to accuse students of cheating, with internal documents from Australian Catholic University showing nearly 6,000 misconduct referrals in a year, 90% involving suspe…
PDF Insight, a new local-first AI tool, sorts and merges PDFs entirely on-device using Ollama and Tesseract, with no upload or internet required. It targets tax preparers and individuals organizing documents, offering an…
Thousands of people believe chatbots like ChatGPT are conscious, yet no one attributes the same to image generators like Midjourney, despite similar underlying technology. This dichotomy highlights a persistent tendency …
Google is testing Gmail Live, a voice search feature for its email service, on Android and iOS. The tool, announced at I/O 2026, allows users to search their inbox conversationally using natural language and will roll ou…
Barcelona Supercomputing Center submitted an end-to-end system combining a speech encoder with a translation-oriented large language model to the instruction following track of IWSLT 2026. The system uses a chain-of-thou…
Researchers presented AURA-ST, a three-stage modular pipeline for low-resource speech-to-text translation at IWSLT 2026. The system bypasses traditional cross-attention by treating projected acoustic representations as t…
Researchers from KIT submitted a cross-lingual voice cloning system to the IWSLT 2026 track, building on FishAudio-S2-Pro with language tag prompting, reinforcement learning fine-tuning, and reference-conditioned lexical…
A brand context folder with voice profile, visual identity, and positioning files enables consistent, on-brand AI outputs from every session. The folder contains plain-text files written for AI consumption, including voi…
Vertical software companies are transforming analytics from a dashboard feature into the core product, driven by AI agents that let customers query data in plain language. Mews acquired DataChat for hospitality, Procore …
HW-TSC submitted a cascaded system to the IWSLT 2026 Subtitling track, using a large-model-based streaming speech recognition framework with VAD, sliding-window context caching, long audio chunking, and Qwen3 forced alig…
Telnyx launched Arabic speech-to-text and text-to-speech models for its Voice AI platform, enabling voice agents to serve Arabic-speaking customers. The Telnyx.Bayan TTS model and basira STT model can be paired for Arabi…
Developer built Ask the Canon, a semantic search engine over 100 public-domain books, using Hugging Face and NumPy without a vector database or external AI APIs. The system loads 79,292 passages as a 240 MB float32 matri…
Researchers from an undisclosed institution introduced AlignAtt4LLM, the first application of the AlignAtt policy to decoder-only large language models for simultaneous speech translation at IWSLT 2026. The system, a syn…
Researchers from IIIT-BGP presented low-resource Bhojpuri-Hindi speech translation systems at IWSLT 2026, including an end-to-end model combining Wav2Vec2 and NLLB-200 with a lightweight adapter, and a cascaded system us…
The CUHKSZ team submitted a simultaneous speech translation system to IWSLT 2026, built on Qwen3-Omni-30B-A3B with LoRA adaptation, achieving 40.5 BLEU for English→Chinese and 27.7 BLEU for English→German in the 0–2 s la…
Researchers at Ohio State University developed HydraQE, an end-to-end, reference-free quality estimation system for speech translation that outperforms cascaded text-based baselines. Submitted to the IWSLT 2026 shared ta…