Presenting @insee.fr's torchtextclassifier at PyData Global !

A toolkit package for text classification with PyTorch.

Tuesday 12:30 (UTC) - join the session!

#PyDataGlobal #NLP #MachineLearning #PyTorch #TextClassification

github.com/inseefrlab/t...

cfp.pydata.org/pydataglobal...

Codebook Conceptualization Still Key for LLM Text Classification

Skipping a codebook when prompting LLMs can cause systematic conceptualization errors; authors advise a concise codebook and small‑scale human validation. getnews.me/codebook-conceptualizati... #llm #textclassification

Text Classification for a Construction Technology Company Learn more how Hitech BPO helps Germany-based construction Technology Company with text classification and validation of news articles to enhance the AI Models.

Text Classification and Validation for a construction tech company

Want to see it in action?
shorturl.at/7fL9X

#TextClassification #ConstructionIndustry #DataAutomation #CaseStudy #DataAnnotation #Database #Accuracy

Why PEFT Beats FFT in Active Learning: Forgetting Dynamics and Stable Representations

PEFT with AL selects more valuable data, preserves stable early‑layer representations, reduces forgetting, and outperforms FFT in low‑resource settings. #textclassification

Who Learns Faster With Less Data? Adapters Beat Full Fine‑Tuning

Experiments show PEFT, especially Prefix‑tuning and UniPELT, outperform FFT in low‑resource text tasks and remain strong in AL setups, boosted further by TAPT. #textclassification

Teaching Big Models With Less Data: How Adapters + Active Learning Win

This paper studies active learning with parameter‑efficient fine‑tuning (adapters), showing AL+PEFT improves PLMs in low‑resource text classification. #textclassification

A new way to test how well AI systems classify text | MIT News | Massachusetts Institute of Technology Automated online conversations made by text classifiers are becoming more prevalent. Now, an MIT team led by Kalyan Veeramachaneni has come up with an innovative approach to not only measuring how well these classifiers are doing their job, but going one step further to make them more accurate.

About the importance of just one word in biasing text classification

"A new way to test how well #AI systems classify text"

#LLM #TextClassification

news.mit.edu/2025/new-way...

Boosting Transformers: Recognizing Textual Entailment for Classification of Vaccine News Coverage <p xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" class="first" dir="auto" id="d3989791e72"> The introduction of Transformers, neural networks employing self-attention mechanisms, ...

'Boosting Transformers: Recognizing Textual Entailment for Classification of Vaccine News Coverage' - a #ComputationalCommunication Research article from @amsterdamupress.bsky.social on #ScienceOpen:

➡️ www.scienceopen.com/document?vid...

🖇️ #NLP #Transformers #TextClassification #TextualEntailment

Flick: Few Labels Text Classification using K-Aware Intermediate
Learning in Multi-Task Low-Resource Languages
Abdullah Alsuhaibani, Ali Almutairi et al.
Paper
Details
#KAwareLearning #MultitaskLowResource #TextClassification

AI Researchers Put DeepSeek to the Test Study compares DeepSeek against Claude, Gemini, GPT, and Llama in authorship and citation classification, finding that while Claude is the most accurate, DeepSeek offers strong performance at a lower ...

AI Researchers Put DeepSeek to the Test 🧠📊🚀 www.azoai.com/news/2025020... #DeepSeek #AI #MachineLearning #LLMs #TextClassification #AIResearch #Claude #NLP #Tech #FutureAI

New Swedish corpus with 2.3 billion words now in Sketch Engine.

🇸🇪 Hej! The Swedish Web 2020 corpus with over 160 thousand sentences is now available! The texts have been carefully cleaned and classified by genres (blogs, news, …) and topics (arts, health, …). 👉 www.sketchengine.eu/svtenten-swe...
#corpuslinguistics #digitalhumanities #textclassification

The key to mastering #textclassification lies in understanding the power of #RNNs. These neural networks process and remember data, allowing for deeper insights and predictions.

RNNs offer a unique approach to managing large text datasets.
Want to dive deeper? 👉 https://buff.ly/3T5HFmK

SDC explored Gen-AI for text classification: social media abortion posts (GSMA) into Pro-Choice & Pro-Life; AP-NORC open responses into 5 political topics.

✅ GPT-4 outperforms AutoML.
✅ Near 100% accuracy on AP-NORC.
✅ Near 20% improvement on GSMA.

#GenAI #MachineLearning #TextClassification

AI Coder Web site created using create-react-app

Exciting news! After months of hard work, we're launching a game-changing AI-based text classification tool, developed with the amazing Jaxin Lu. Say goodbye to complex coding! futurescape.uwaterloo.ca/ai-coder/ #AI #TextClassification #TechInnovation

#EACL2023 is just around the corner, where we will be showcasing our system demonstration paper "Small-Text: Learning for Text Classification in Python".

The corresponding poster presentation is scheduled for Session 6 on May 3rd, 9:00–10:30 AM.

#NLProc #TextClassification

1/2 https://t.co/i6