Tanmay Bakshi
Ranking Amazon Reviews by Quality with Pointwise Ratings learned from Pairwise Data
#1about 7 minutes
Ranking Amazon reviews by learning a quality score
The model learns to assign a continuous quality score to reviews by training on a classification task rather than a direct regression problem.
#2about 7 minutes
How neural networks learn through feature embeddings
Neural networks transform complex input data into a high-dimensional embedding space where it becomes linearly separable for classification.
#3about 6 minutes
Processing sequential text data with Word2Vec and RNNs
Word2Vec creates semantic vector representations of words, which are then processed sequentially by Recurrent Neural Networks (RNNs) to understand context.
#4about 5 minutes
Identifying the limitations of recurrent neural networks
Recurrent neural networks are slow due to their sequential nature, lack general-purpose understanding, and struggle to process bidirectional context simultaneously.
#5about 8 minutes
Introducing the BERT and transformer architecture
The Transformer architecture uses self-attention to process text in parallel, enabling BERT to learn general, contextual word representations through masked language modeling.
#6about 6 minutes
Demonstrating self-attention with a character-level model
A simplified character-level model called 'Artist BERT' demonstrates how self-attention works by predicting masked characters in artist names.
#7about 8 minutes
Training a pointwise ranker from pairwise review data
A Siamese network architecture processes pairs of reviews to determine which is better, implicitly learning a pointwise quality score for each individual review.
Related jobs
Jobs that call for the skills explored in this talk.
Wilken GmbH
Ulm, Germany
Senior
Kubernetes
AI Frameworks
+3
Matching moments
03:13 MIN
How AI can create more human moments in HR
The Future of HR Lies in AND – Not in OR
06:51 MIN
Balancing business, technology, and people for holistic success
The Future of HR Lies in AND – Not in OR
03:28 MIN
Shifting from talent acquisition to talent architecture
The Future of HR Lies in AND – Not in OR
05:10 MIN
How the HR function has evolved over three decades
The Future of HR Lies in AND – Not in OR
06:59 MIN
Moving from 'or' to 'and' thinking in HR strategy
The Future of HR Lies in AND – Not in OR
06:04 MIN
The importance of a fighting spirit to avoid complacency
The Future of HR Lies in AND – Not in OR
06:10 MIN
Understanding global differences in work culture and motivation
The Future of HR Lies in AND – Not in OR
04:22 MIN
Navigating ambiguity as a core HR competency
The Future of HR Lies in AND – Not in OR
Featured Partners
Related Videos
35:16How AI Models Get Smarter
Ankit Patel
47:28What do language models really learn
Tanmay Bakshi
57:52Develop AI-powered Applications with OpenAI Embeddings and Azure Search
Rainer Stropek
56:46A beginner’s guide to modern natural language processing
Jodie Burchell
28:07How we built an AI-powered code reviewer in 80 hours
Yan Cui
38:24Machine learning in the browser with TensorFlowjs
Håkan Silfvernagel
32:54The pitfalls of Deep Learning - When Neural Networks are not the solution
Adrian Spataru & Bohdan Andrusyak
25:19Mastering Image Classification: A Journey with Cakes
Carly Richmonds
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
Imec
Azure
Python
PyTorch
TensorFlow
Computer Vision
+1
autonomous-teaming
Berlin, Germany
Remote
ETL
NoSQL
NumPy
Python
+3
autonomous-teaming
München, Germany
Remote
C++
GIT
Linux
Python
+1
Amazon.com, Inc.
Barcelona, Spain
XML
HTML
JSON
Python
Scripting (Bash/Python/Go/Ruby)
Amazon.com Inc.
Senior
R
API
Python
Matlab
Bootstrap
+4
Amazon.com Inc.
Senior
R
API
Unix
Perl
Ruby
+7
autonomous-teaming
Canton of Toulouse-5, France
Remote
C++
GIT
Linux
Python
+1
Amazon.com, Inc
Shoreham-by-Sea, United Kingdom
XML
HTML
JSON
Python
Data analysis
+1
autonomous-teaming
Canton of Toulouse-5, France
Remote
ETL
NoSQL
NumPy
Python
+4