SpaCy
PulseAugur coverage of SpaCy — every cluster mentioning SpaCy across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New research compares PII redaction methods for LLM pipelines
A new research paper compares four methods for redacting personally identifiable information (PII) before sending text to large language models (LLMs). The study evaluated pure regular expressions (regex), Microsoft Pre…
-
New framework integrates lexical and semantic methods for discourse analysis
A research paper proposes a hybrid framework for quantitative discourse analysis that integrates lexical and semantic methods. This approach aims to enhance transparency, reproducibility, and interpretability in computa…
-
AI/ML Tech Review: Scikit-learn, LangGraph, and 60 others evaluated
A review of 62 AI and ML technologies highlights which tools are consistently chosen for repeat use, alongside five that are on hold and areas of disagreement among evaluators. The analysis covers a broad spectrum of li…
-
Build Secure Document Pipeline with OpenCV, Presidio, and LangGraph
This tutorial guides developers in building a secure document processing pipeline called SecureKiosk AI. The system uses local tools like OpenCV and Tesseract for image processing and text extraction, followed by Micros…
-
Python script extracts entities from text using spaCy
A Python script has been developed to perform Named Entity Recognition (NER) on raw text, extracting organizations, persons, and geopolitical entities. This intermediate-level tool, written in 216 lines of Python code, …
-
On-device NER models evaluated for accuracy, cost, and reliability
A new study published on arXiv evaluates nine named-entity recognition (NER) systems for on-device deployment, considering accuracy, cost, reliability, and confidence. The research compares classical taggers, bidirectio…
-
Telveguard AI Gateway Masks Turkish Personal Data for Compliance
An open-source AI gateway called Telveguard has been developed to help companies comply with data protection laws, particularly in Turkey. The tool acts as a reverse proxy, masking sensitive personal data like Turkish I…
-
New dataset HUMAID-NER aids disaster tweet analysis
Researchers have introduced HUMAID-NER, a novel dataset designed for extracting structured information from disaster-related tweets. This dataset, built upon the HumAID benchmark, contains 60,000 English disaster tweets…
-
Open-source tool adds governance to Anthropic's Claude API
A developer has created an open-source Python library called enterprise-claude-kit to add a governance layer for the Anthropic Claude API. This layer sits between an application and the Claude API, providing features su…
-
New Study Reveals PII Detection Systems Fail Under Realistic Data Shifts
A new research paper titled "Mind the Gap: Robustness Risks in PII Detection Systems" highlights significant vulnerabilities in current Personally Identifiable Information (PII) detection systems. The study, which evalu…
-
Executable Rubrics Framework Enhances LLM Evaluation Efficiency
Researchers have introduced ExecRubrics, a new framework that represents evaluation rubrics as executable Python programs. This approach aims to improve transparency and efficiency in language model evaluation by provid…
-
New spaCy-based POS tagger achieves high accuracy for Scottish Gaelic
Researchers have developed a part-of-speech tagger for Scottish Gaelic, an endangered and morphologically complex language, using the spaCy Natural Language Processing framework. Two models were trained with minimal pre…
-
New method enhances VLM interpretability in medicine
Researchers have developed ParseFIxLIP, a novel method to improve the interpretability of Vision-Language Models (VLMs) in medical applications. This new approach integrates Tree-Gram Parsing into the Banzhaf interactio…
-
New toolkit enhances syntactic analysis of child-adult language interactions
Researchers have developed a new open-source toolkit called CAIT, designed to improve the syntactic analysis of child-adult interactions within the CHILDES corpus. This toolkit includes a specialized dependency parser t…
-
Claude Code's 'Extended Thinking' output found to be inauthentic
A recent discovery has revealed that the 'Extended Thinking' output generated by Claude Code, an AI model, is not authentic. This finding raises concerns about the reliability and trustworthiness of AI-generated content…
-
New dataset boosts NLP for Malaysian English
Researchers have developed a new dataset called the Malaysian English News (MEN) dataset, containing 200 news articles annotated with entities and relations. This resource aims to improve Natural Language Processing (NL…
-
New pipeline creates NLP resource for historical Greek parliamentary text
Researchers have developed a new, reproducible pipeline for creating a Universal Dependencies-style parsing resource for Katharevousa Greek parliamentary text. This workflow addresses the limitations of current NLP tool…
-
New toolkit CAIT enhances syntactic analysis of child-adult language interactions
Researchers have developed CAIT, a new open-source toolkit designed to analyze the syntactic structure of child-adult interactions within the CHILDES dataset. This toolkit includes a state-of-the-art dependency parser t…
-
NLP tools compare toponym identification and topic models for climate event news
Two new research papers explore natural language processing techniques for analyzing news coverage of extreme climate events in German media. One paper compares the performance of off-the-shelf Named Entity Recognition …
-
FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting
Researchers have developed a new framework called FGDM for detecting and repairing software bugs. This multi-agent system leverages Large Language Models (LLMs) with Chain-of-Thought and Tree-of-Thoughts prompting to un…