National Edu News: IIT Hyderabad-NHAI sign MoU for Transportation Research  |  Cover Story: Elimination Round or Aptitude Test- How to Align CUET with NEP 2020 Goals  |  Life Inspirations: Master of a Dog House  |  Education Information: Climate Predictions: Is it all a Piffle!  |  Leadership Instincts: Raj Mashruwala Establishes CfHE Vagbhata Chair in Medical Devices at IITH   |  National Edu News: TiHAN supports a Chair for Prof Srikanth Saripalli at IIT Hyderabad  |  Teacher Insights: How To Build Competitive Mindset in Children Without Stressing Them  |  Parent Interventions: What Books Children Must Read this Summer Vacation   |  Policy Indications: CUET Mandatory for Central Universities  |  Teacher Insights: Classroom Dialogue for a Better World  |  Rajagiri Round Table: Is Time Ripe for Entrepreneurial Universities in India?  |  Life Inspirations: How to Overcome Fear of Public Speaking  |  Parent Interventions: Wide Ranging Problems of Preterm Infants  |  Technology Inceptions: Smart IoT-based, indigenously-developed, ICU Ventilator “Jeevan Lite” Launched  |  Parent Interventions: Meditation Reduces Guilt Feeling  |  
July 27, 2019 Saturday 09:51:27 AM IST

Statistical Method Identified to Detect Fake or Computer-Generated Text

By Felix Litchenfeld

Researchers at Harvard John A Paulson School of Engineering and Applied Sciences (SEAS) and IBM have developed a statistical method to detect computer-generated or fake text from human generated text.
Researchers Sebastian Gehrmann and Hendrik Strobert(IBM) found that natural-language generators are trained on tens of millions of online texts and mimic human language by predicting the words that most often follow one another. For eg I followed by 'have' and 'am'. Using this idea they developed a method that identifies predictable text instead of flagging errors. Gehrmann and Strobelt’s method, known as GLTR, is based on a model trained on 45 million texts from websites — the public version of the OpenAI model, GPT-2. Because it uses GPT-2 to detect generated text, GLTR works best against GPT-2, but it does well against other models, too.


https://news.harvard.edu/gazette/story/2019/07/researchers-develop-a-method-to-identify-computer-generated-text/?utm_medium=Feed&utm_source=Syndication



Comments