Advertisement
Check these out next
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Sep. 24, 2020•0 likes•89 views
0 likes
Be the first to like this
Show More
views
Total views
0
On Slideshare
0
From embeds
0
Number of embeds
0
Download to read offline
Report
Technology
In this talk, Frederick Liu from Google talks about feature attribution on text classification. Presented on 07/17/2019 **These slides are from a talk given at Rsqrd AI. Learn more at rsqrdai.org**
Sanjana ChowdhuryFollow
Advertisement
Advertisement
Advertisement
Recommended
SearchLove San Diego 2017 | Annie Cushing | Avoid Panic Attacks With a First ...Distilled
How to Raise a Robot Army #dddperthMichelle Sandford
FlyerBlastinBubblesJames Durkin
Code is so much more...Praveen Puglia
Rsqrd AI: Making Conversational AI Work for EverybodySanjana Chowdhury
Rsqrd AI: Application of Explanation Model in HealthcareSanjana Chowdhury
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
- Proprietary + Confidential Frederick Liu 7/17/19 @ Robust AI Incorporating priors with feature attribution on text classification
- Proprietary + ConfidentialProprietary + Confidential Machine learning .6 .2 .1 .3 .7 .1 .8 .7 .5.3 .1 .4 .9 .2 .0 .6.8 .2.1.6Toxic … … … … … … … Neutral … … … … … … Toxic … … … … … … … Toxic … … … … … … Neutral … … … … … … Training Inference Gay pride is in June. .6 .2 .1 .3 .7 .1 .8 .7 .5.3 .1 .4 .9 .2 .0 .6.8 .2.1.6 95% Toxic
- Proprietary + ConfidentialProprietary + Confidential Machine learning + Explainability .6 .2 .1 .3 .7 .1 .8 .7 .5.3 .1 .4 .9 .2 .0 .6.8 .2.1.6Toxic … … … … … … … Neutral … … … … … … Toxic … … … … … … … Toxic … … … … … … Neutral … … … … … … Training Inference Gay pride is in June. .6 .2 .1 .3 .7 .1 .8 .7 .5.3 .1 .4 .9 .2 .0 .6.8 .2.1.6 95% Toxic Gay Pride is in June 90% 1% 1% 1% 2%
- Proprietary + ConfidentialProprietary + Confidential Machine learning + Regularization Toxic … … … … … … … Neutral … … … … … … Toxic … … … … … … … Toxic … … … … … … Neutral … … … … … … Training Inference Gay pride is in June. .5 .2 .1 .3 .5 .1 .5 .5 .5.3 .1 .4 .5 .2 .0 .5.5 .2.1.5 85% Toxic .5 .2 .1 .3 .5 .1 .5 .5 .5.3 .1 .4 .5 .2 .0 .5.5 .2.1.5
- Proprietary + ConfidentialProprietary + Confidential Machine learning + Regularization + Explainability Toxic … … … … … … … Neutral … … … … … … Toxic … … … … … … … Toxic … … … … … … Neutral … … … … … … Training Inference Gay pride is in June. 15% Toxic Gay Pride is in June He is an impolite gay 0% .7 .2 .1 .3 .7 .1 .7 .5.3.4 .9 .2 .1 .6.8 .20. 1 .1 .2 .5 .7 .2 .1 .3 .7 .1 .7 .5.3.4 .9 .2 .1 .6.8 .20. 1 .1 .2 .5 + person
- Proprietary + ConfidentialProprietary + Confidential Regularizing + Explainability → Controllability .6 .2 .1 .3 .7 .1 .8 .7 .5.3 .1 .4 .9 .2 .0 .6.8 .2 .1.6 Explanation
- Proprietary + ConfidentialProprietary + Confidential Regularizing + Explainability → Controllability .6 .2 .1 .3 .7 .1 .3 .7 .5.3 .9 .4 .9 .2 .0 .6.8 .4 .1.7 Explanation More Red! Less Green!
- Proprietary + ConfidentialProprietary + Confidential Explainability - Integrated Gradients Link to paper - https://arxiv.org/pdf/1703.01365.pdf
- Proprietary + ConfidentialProprietary + Confidential Explainability + Regularization
- Proprietary + ConfidentialProprietary + Confidential Results - Classification Metric
- Proprietary + ConfidentialProprietary + Confidential Results - Fairness Metric
- Proprietary + ConfidentialProprietary + Confidential Results - Shift in embedding
- Proprietary + Confidential Thank You Link to paper - https://arxiv.org/pdf/1906.08286.pdf Sign up if you want to know more: bit.ly/model-interpret-interest
Advertisement