Beyond word embeddings

Download as PPTX, PDF

2 likes237 views

The document discusses various methods and models related to AI, including a tree-structured bidirectional LSTM sentiment classification model. It emphasizes the importance of understanding subject-predicate structures and provides several sources for further reading on compositional semantics. The text also references resources for data preparation, model training, and deployment in Azure and GitHub repositories.

Technology

Rob Speer
how-to-make-a-racist-ai-without-
really-trying.ipynb
From Agrawal et al.
Rob Speer
how-to-make-a-
racist-ai-without-
really-trying.ipynb

Iyyer and collaborators broke the tree-structured
bidirectional LSTM sentiment classification model.

The tale of Mr. Morton gives a great intro to
Subject predicate structure. What ever the
predicate says he does.
Source https://people.eecs.berkeley.edu/~klein/cs294-7/SP07%20cs294%20lecture%2019%20--
%20compositional%20semantics%20(6pp).pdf and https://web.stanford.edu/~jurafsky/slp3/22.pdf

Prepare
Data
Register &
Manage Model
Train & Test
Model
Build
Image
…
Build model
(your favorite IDE)
Deploy Service &
Monitor Model
Prepare Experiment Deploy

https://azure.microsoft.com/en-us/services/virtual-
machines/data-science-virtual-machines/?WT.mc_id=beyondembeddings-
powerpoint-abornst
https://docs.microsoft.com/en-
us/python/api/overview/azure/ml/intro?view=azure-ml-
py?WT.mc_id=beyondembeddings-powerpoint-abornst
https://github.com/Azure/MachineLearningNotebooks
https://github.com/allenai/allennlp
https://github.com/aribornstein/pyNeurboParser

Beyond word embeddings

13. - - - - - -

14. - - - - - - - -

18. Rob Speer how-to-make-a-racist-ai-without- really-trying.ipynb From Agrawal et al. Rob Speer how-to-make-a- racist-ai-without- really-trying.ipynb

19. From Iyyer and collaborators.

20. Iyyer and collaborators broke the tree-structured bidirectional LSTM sentiment classification model.

30. The tale of Mr. Morton gives a great intro to Subject predicate structure. What ever the predicate says he does. Source https://people.eecs.berkeley.edu/~klein/cs294-7/SP07%20cs294%20lecture%2019%20-- %20compositional%20semantics%20(6pp).pdf and https://web.stanford.edu/~jurafsky/slp3/22.pdf

31. The tale of Mr. Morton gives a great intro to Subject predicate structure. What ever the predicate says he does. Source https://people.eecs.berkeley.edu/~klein/cs294-7/SP07%20cs294%20lecture%2019%20-- %20compositional%20semantics%20(6pp).pdf and https://web.stanford.edu/~jurafsky/slp3/22.pdf

32. The tale of Mr. Morton gives a great intro to Subject predicate structure. What ever the predicate says he does. Source https://people.eecs.berkeley.edu/~klein/cs294-7/SP07%20cs294%20lecture%2019%20-- %20compositional%20semantics%20(6pp).pdf and https://web.stanford.edu/~jurafsky/slp3/22.pdf

33. The tale of Mr. Morton gives a great intro to Subject predicate structure. What ever the predicate says he does. Source https://people.eecs.berkeley.edu/~klein/cs294-7/SP07%20cs294%20lecture%2019%20-- %20compositional%20semantics%20(6pp).pdf and https://web.stanford.edu/~jurafsky/slp3/22.pdf

35. JAMR Parser

46. Prepare Data Register & Manage Model Train & Test Model Build Image … Build model (your favorite IDE) Deploy Service & Monitor Model Prepare Experiment Deploy

49. https://azure.microsoft.com/en-us/services/virtual- machines/data-science-virtual-machines/?WT.mc_id=beyondembeddings- powerpoint-abornst https://docs.microsoft.com/en- us/python/api/overview/azure/ml/intro?view=azure-ml- py?WT.mc_id=beyondembeddings-powerpoint-abornst https://github.com/Azure/MachineLearningNotebooks https://github.com/allenai/allennlp https://github.com/aribornstein/pyNeurboParser

Editor's Notes

#6: And then share that code around the world

Beyond word embeddings

More Related Content

More from Aaron (Ari) Bornstein (12)

Recently uploaded (20)

Beyond word embeddings

Editor's Notes