Thursday, April 15, 2021
  • Setup menu at Appearance » Menus and assign menu to Top Bar Navigation
Advertisement
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News
No Result
View All Result
NikolaNews
No Result
View All Result
Home Machine Learning

Google reclaiming identity labels to improve machine learning abuse filters

March 31, 2019
in Machine Learning
Google reclaiming identity labels to improve machine learning abuse filters
586
SHARES
3.3k
VIEWS
Share on FacebookShare on Twitter

Credit: Google News

Train a machine learning model to detect ‘toxic’ words in online comments and it comes to some depressing conclusions.

You might also like

Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization

Global Machine Learning Market In-Depth Qualitative Insights & Future Growth Analysis 2021-2027 – The Courier

Seminar on Machine Learning Techniques in Banking – India Education| Global Education |Education News

During Google’s ongoing work on Perspective, an API that uses machine learning to detect abuse and harassment online, engineers found the models identified sentences that use words such as ‘gay’, ‘lesbian’ or ‘transgender’ as abusive.

“Unfortunately what happens when we give it this input – I’m a proud gay person – is the model predicts this is toxic,” said Google AI senior software engineer Ben Hutchinson at an ethics of data science conference at the University of Sydney last week.

“And the reason this happens, it seems, is because the majority of language on the internet on which this model was trained, which uses the word ‘gay’, is in language that is used to abuse and harass people. So the model has learnt the pattern that the word ‘gay’ is a toxic word,” he explained.

The impact of that conclusion finding its way back into online moderation tools is a serious one.

“Models like this are being deployed on website to automatically moderate comments and if we started blocking online comments like this one [I am a young proud gay male living with HIV] we take the voice away from marginalised communities,” Hutchinson said.

The issue is that identity labels like ‘gay’, ‘lesbian’ or ‘transgender’ are over-represented in abusive and toxic online comments. It follows that based on this data, the machine learning models attach negative connotations to the labels.

It’s not the models’ fault: Hutchinson likens them to the jinns, genies and golems found in ancient folklore. They are a non-human intelligence, he says, that “are neither inherently good nor inherently evil, but they are prone to misinterpreting things”.

“The important question is not is our model learning patterns from the data correctly? But rather how do we want our systems to impact people?” Hutchinson added.


Read more Stay ‘frustrated’ at tech companies post-Christchurch attack, says Microsoft president

To overcome what the machine learning community refers to as insufficient diversity in the training data, Google in March last year set about collecting statements about how marginalised group describe themselves and loved ones.

Throughout 2018, stalls were set up at Sydney Gay and Lesbian Mardi Gras, Auckland Pride and San Francisco Pride events. Attendees were invited to anonymously write down the identity labels they might give themselves and make a statement describing themselves and the ones they love. The labels and statements are still being collected online.

“It’s really important to go out there and get the data you need,” Hutchinson said. “The idea is to create a targeted test data set specifically aimed at testing whether models have harmful biases for a particular community using the language which they use.”

Armed with the new datasets, Hutchinson and team are now able to better understand at which points in neural networks models are determining an identity label is toxic by “peering inside the network”. They do this using a method called Concept Activation Vectors.


Read more Google fined €1.49 billion for search ad blocks in third EU sanction

“The idea here is that we can take an input – such as ‘I’m an out gay person’ – we can pass it through a series of layers of our network, and then stop at one of the internal layers and look at the strengths of the activations of the nodes in that layer,” Hutchinson explained.

Essentially the techniques allow for two important things, Hutchinson said.

“Normative testing – how do we know that model we’ve trained is actually working in accordance with our human social norms and values, and the second goal is interpretability – we’d like to know if the model is misinterpreting what it is that we’re trying to do,” he explained.

The labels and statements – which continue to be collected online and in-person as part of Project Respect – will, later this year, go into an open source dataset so developers can it to teach their own machine learning models which words people use to positively identify themselves.


Read more Social media, ISP execs to face PM grilling over role in spreading hate

“The hope is that by expanding the diversity of training data, these models will be able to better parse what’s actually toxic and what’s not,” Hutchinson said.

Join the newsletter!

Error: Please check your email address.

Tags Googlemachine learningNeural NetworksmoderationtoxicGoogle AIartificial intelligenceonline comments

More about GoogleUniversity of Sydney


Credit:
Google News

Previous Post

Popup enlarges at the last second so users click on ads instead of 'Close' button

Next Post

Educating for AI – one of the most critical problems in AI

Related Posts

Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization
Machine Learning

Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization

April 14, 2021
Global Machine Learning Market In-Depth Qualitative Insights & Future Growth Analysis 2021-2027 – The Courier
Machine Learning

Global Machine Learning Market In-Depth Qualitative Insights & Future Growth Analysis 2021-2027 – The Courier

April 14, 2021
Seminar on Machine Learning Techniques in Banking – India Education| Global Education |Education News
Machine Learning

Seminar on Machine Learning Techniques in Banking – India Education| Global Education |Education News

April 14, 2021
Applying artificial intelligence to science education — ScienceDaily
Machine Learning

Machine learning can help slow down future pandemics — ScienceDaily

April 14, 2021
ML Ops and the Promise of Machine Learning at Scale
Machine Learning

ML Ops and the Promise of Machine Learning at Scale

April 14, 2021
Next Post
Educating for AI – one of the most critical problems in AI

Educating for AI – one of the most critical problems in AI

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Recommended

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

Plasticity in Deep Learning: Dynamic Adaptations for AI Self-Driving Cars

January 6, 2019
Microsoft, Google Use Artificial Intelligence to Fight Hackers

Microsoft, Google Use Artificial Intelligence to Fight Hackers

January 6, 2019

Categories

  • Artificial Intelligence
  • Big Data
  • Blockchain
  • Crypto News
  • Data Science
  • Digital Marketing
  • Internet Privacy
  • Internet Security
  • Learn to Code
  • Machine Learning
  • Marketing Technology
  • Neural Networks
  • Technology Companies

Don't miss it

Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization
Machine Learning

Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization

April 14, 2021
Data Labeling Service — How to Get Good Training Data for ML Project? | by ByteBridge | Apr, 2021
Neural Networks

Data Labeling Service — How to Get Good Training Data for ML Project? | by ByteBridge | Apr, 2021

April 14, 2021
The Search Engine Land Awards are open: Wednesday’s daily brief
Digital Marketing

The Search Engine Land Awards are open: Wednesday’s daily brief

April 14, 2021
Six courses to build your technology skills in 2021 – IBM Developer
Technology Companies

IBM joins Eclipse Adoptium and offers free certified JDKs with Eclipse OpenJ9 – IBM Developer

April 14, 2021
Cyber criminals are installing cryptojacking malware on unpatched Microsoft Exchange servers
Internet Security

Cyber criminals are installing cryptojacking malware on unpatched Microsoft Exchange servers

April 14, 2021
Simplify, then Add Lightness – Consolidating the Technology to Better Defend Ourselves
Internet Privacy

Simplify, then Add Lightness – Consolidating the Technology to Better Defend Ourselves

April 14, 2021
NikolaNews

NikolaNews.com is an online News Portal which aims to share news about blockchain, AI, Big Data, and Data Privacy and more!

What’s New Here?

  • Sailthru Announces Machine Learning Features for Improved Lifecycle Optimization April 14, 2021
  • Data Labeling Service — How to Get Good Training Data for ML Project? | by ByteBridge | Apr, 2021 April 14, 2021
  • The Search Engine Land Awards are open: Wednesday’s daily brief April 14, 2021
  • IBM joins Eclipse Adoptium and offers free certified JDKs with Eclipse OpenJ9 – IBM Developer April 14, 2021

Subscribe to get more!

© 2019 NikolaNews.com - Global Tech Updates

No Result
View All Result
  • AI Development
    • Artificial Intelligence
    • Machine Learning
    • Neural Networks
    • Learn to Code
  • Data
    • Blockchain
    • Big Data
    • Data Science
  • IT Security
    • Internet Privacy
    • Internet Security
  • Marketing
    • Digital Marketing
    • Marketing Technology
  • Technology Companies
  • Crypto News

© 2019 NikolaNews.com - Global Tech Updates