Natural Language Processing news and analysis on Web Pulse: 5446 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Voiset released Voiset 2.0 on August 24, adding full Arabic support, a rebuilt AI planning engine, and a Model Context Protocol integration that lets users manage their day from inside Claude without opening the app. The…
Zendesk's CX Trends 2026 survey found that 83% of CX leaders view memory-rich AI as key to personalized customer journeys, while 74% of surveyed customers are frustrated at having to repeat information and 81% want an ag…
Code Magnet published a beginner-friendly guide on building a vector search engine from scratch in pure Python, using only the standard library (re, math, collections) and implementing TF-IDF and cosine similarity. The g…
Famulor added Inworld as a new voice provider for AI assistants in an update dated August 30, 2026, offering two selectable voice variants, according to the Famulor changelog. Famulor positions the Inworld option for pre…
Verba, an open-source language-learning app, lets users practice eight languages through conversations with an AI that runs entirely offline on their machine, with no account or server required. The app, available for ma…
Google is rolling out a new “Turn on live translation” option for Gemini Live, enabling real-time translation of spoken conversations between languages, with captions appearing as the conversation continues. The feature,…
Gradium has made a new text-to-speech model the default for its API and Studio, claiming an 81.0% hard-case pass rate and 216 ms median time to first audio on Coval's TTS benchmark. The model, live since August 31, 2026,…
A new arXiv preprint (2608.28666v1) introduces structured video prompting, a training-free inference-time method that augments input videos with spatial and temporal structure to improve spatial-temporal reasoning in vid…
Researchers introduced HANIA, a planner-guided multimodal graph framework for evidence-grounded question answering, which uses a frozen vision-language model and a two-group finite-state planner to select concise, releva…
Researchers released RegDivergence-101, a 101-pair benchmark for detecting regulatory contradictions between FDA and EMA guidance in life sciences, with an LLM judge (Claude Haiku) achieving 0.830 macro-F1, outperforming…
Researchers introduced HERBIOME, a modular pipeline for automated herbarium label digitization that integrates YOLOv8-based detection, CRAFT Hezar text localization, fine-tuned TrOCR, and GPT-4o Mini, achieving a Charact…
Researchers introduced PromptKWS, a prompt-guided open-vocabulary keyword spotting framework that improves wakeup rate by over 10% and average accuracy by over 15% in noisy, real-world conditions compared to baseline aco…
A new arXiv study (2608.28645v1) found that three large language models—Llama3, Hex-1, and Sarvam—showed script-dependent improvement in classifying legal complaints in the low-resource Dravidian language Tulu when queri…
Keenable.ai has open-sourced NEEDLE, a live search benchmark that generates fresh queries hourly or daily from public data sources to prevent search engines from memorizing test answers, and it evaluates 15 search APIs a…
A new open-source skill called Deslop, created by developer fayerman-source, teaches AI coding assistants and agentic frameworks such as Google Antigravity, Gemini CLI, and Claude Code to rewrite legalese and verbose AI-…
A study presented at the 17th Conference of the Association for Machine Translation in the Americas (AMTA 2026) finds that large language models with 70B parameters or more consistently improve downstream machine transla…
Researchers at the Association for Machine Translation in the Americas found that document-level summaries improve AI-based post-editing quality only when they are specific and actionable, with gemini-2.5-flash-lite summ…
A study by researchers including Jeniffer Leal-Wyss, Gabriel Bernier-Colborne, Delaney Lothian, Michel Simard, and Rebecca Knowles, presented at the 17th Conference of the Association for Machine Translation in the Ameri…
A study presented at the 17th Conference of the Association for Machine Translation in the Americas (AMTA 2026) benchmarked eight large language models on game localization quality assurance tasks, finding that Claude So…
Researchers Ming Qian and Luyi Yang found that GPT5, guided by MQM-like prompts, aligned with human evaluators on 77.8% of negative flags and 88.9% of positive flags, with an F1 score of 0.875 for detailed rationales, in…