Education Information: Degree College Teachers Training Programme from 22nd Nov to 12th Dec 2019  |  Career News: ANNOUNCEMENT FOR THE POST OF JOINT DIRECTOR, (NCERT)  |  National Edu News: UGC guidelines on plastic use  |  International Edu News: Asian students converge on 5 countries  |  Health Monitor: Playing With Fire  |  Finance: Trading in an Uncertain World   |  Technology Inceptions: Scientists are Wearing VR Goggles to Analyse Data  |  International Edu News: Macquarie University's Biofoundry to Set Up Synthetic Biology Center  |  Parent Interventions: Alcohol Consumption in Pregnancy Alters Babies' DNA  |  Technology Inceptions: EDantseva, app on Oral Health Released   |  Science Innovations: Two Physicists Win Nobel Prize for Discovery of Exoplanets  |  Science Innovations: Celebrate Diwali With Environment Friendly 'Green' Crackers  |  Personal Counseling: Learning Disorders  |  Creative Living: Born to be a Unicorn: Saga of d’Alembert  |  Rajagiri Round Table: Teaching in The Time of AI  |  
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