Content - fb9a9b3f6ae381892c943ea8a1ffc56034477fb6 - b1cf431/Tutorials/SLUHandsOn/README.md

swh:1:snp:f50ab94432af916b5fb8b4ad831e8dddded77084

Tip revision: a05c3c642648373f4ede0956e4286257c3d59a61 authored by liqfu on 24 August 2018, 17:46:51 UTC
CNTK splice allows broadcast. This case is handled in the change. For noop (identity) ops, its inputs and outputs types shall be set according to upstream ops. ToBatch/ToSequence and Unpack Batch/Sequence ops added during model importing need tp be skipped. Model import need to handle ops with multiple outputs.

Tip revision: a05c3c6

README.md

# CNTK Tuturial: Language Understanding

## Overview

This hands-on lab shows how to implement a recurrent network to process text, for the Air Travel Information Services (ATIS) tasks of slot tagging and intent classification. We will start with a straight-forward embedding followed by a recurrent LSTM. We will then extend it to include neighbor words and run bidirectionally. Lastly, we will turn this system into an intent classifier.

## Tutorial

Please find a detailed tutorial that uses the data and configurations in this folder on our website at https://docs.microsoft.com/en-us/cognitive-toolkit/Hands-On-Labs-Language-Understanding.