GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → ajinkyaT → Cnn_intent_classification

ajinkyaT / Cnn_intent_classification

CNN for intent classification task in a Chatbot

Labels

jupyter-notebookkerascnnchatbottext-classification

Projects that are alternatives of or similar to Cnn intent classification

Embedded gcnn
Embedded Graph Convolutional Neural Networks (EGCNN) in TensorFlow
Stars: ✭ 60 (-33.33%)
Mutual labels:  jupyter-notebook, cnn
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: ✭ 65 (-27.78%)
Mutual labels:  jupyter-notebook, cnn
Sentiment analysis albert
sentiment analysis、文本分类、ALBERT、TextCNN、classification、tensorflow、BERT、CNN、text classification
Stars: ✭ 61 (-32.22%)
Mutual labels:  cnn, text-classification
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: ✭ 57 (-36.67%)
Mutual labels:  jupyter-notebook, cnn
Nlp Tutorial
A list of NLP(Natural Language Processing) tutorials
Stars: ✭ 1,188 (+1220%)
Mutual labels:  jupyter-notebook, text-classification
One Pixel Attack Keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
Stars: ✭ 1,097 (+1118.89%)
Mutual labels:  jupyter-notebook, cnn
Lstm Cnn classification
Stars: ✭ 64 (-28.89%)
Mutual labels:  cnn, text-classification
Face Identification With Cnn Triplet Loss
Face identification with cnn+triplet-loss written by Keras.
Stars: ✭ 45 (-50%)
Mutual labels:  jupyter-notebook, cnn
Char Cnn Text Classification Tensorflow
Character-level Convolutional Networks for Text Classification论文仿真实现
Stars: ✭ 72 (-20%)
Mutual labels:  cnn, text-classification
Cnn Interpretability
🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
Stars: ✭ 68 (-24.44%)
Mutual labels:  jupyter-notebook, cnn
Text nn
Text classification models. Used a submodule for other projects.
Stars: ✭ 55 (-38.89%)
Mutual labels:  jupyter-notebook, cnn
Pytorch
PyTorch tutorials A to Z
Stars: ✭ 87 (-3.33%)
Mutual labels:  jupyter-notebook, cnn
Very Deep Convolutional Networks For Natural Language Processing In Tensorflow
implement the paper" Very Deep Convolutional Networks for Natural Language Processing"(https://arxiv.org/abs/1606.01781 ) in tensorflow
Stars: ✭ 54 (-40%)
Mutual labels:  jupyter-notebook, text-classification
Applied Text Mining In Python
Repo for Applied Text Mining in Python (coursera) by University of Michigan
Stars: ✭ 59 (-34.44%)
Mutual labels:  jupyter-notebook, text-classification
Lung Diseases Classifier
Diseases Detection from NIH Chest X-ray data
Stars: ✭ 52 (-42.22%)
Mutual labels:  jupyter-notebook, cnn
Deeplearning Nlp Models
A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.
Stars: ✭ 64 (-28.89%)
Mutual labels:  jupyter-notebook, cnn
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (-54.44%)
Mutual labels:  jupyter-notebook, cnn
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: ✭ 44 (-51.11%)
Mutual labels:  jupyter-notebook, cnn
Text Analytics With Python
Learn how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python! This repository contains code and datasets used in my book, "Text Analytics with Python" published by Apress/Springer.
Stars: ✭ 1,132 (+1157.78%)
Mutual labels:  jupyter-notebook, text-classification
Understaing Datasets Estimators Tfrecords
Try to use tf.estimator and tf.data together to train a cnn model.
Stars: ✭ 76 (-15.56%)
Mutual labels:  jupyter-notebook, cnn
View All Similar Projects ➔

Intent classification for a chatbot using Convolutional Neural Networks

This is Keras implementation for the task of sentence classification using CNNs.

Dataset for the above task was obtained from the project Natural Language Understanding benchmark

Text used for the training falls under the six categories namely, AddToPlaylist, BookRestaurant, GetWeather , RateBook , SearchCreativeWork, SearchScreeningEvent each having nearly 2000 sentences.

To prepare the dataset, from the main project's directory, open terminal and type:

$ python prepare_data.py

Check Intent_Classification_Keras_Glove.ipynb for the model building and training part. Below is the model overview.

image

Although RNN's like LSTM and GRU are widely used for language modelling tasks but CNN's have also proven to be quite faster to train owing to data parallelization while training and give better results than the LSTM ones. Here is a brief comparison between different methods to solve sentence classification, as can be seen TextCNN gives best result of all and also trains faster. I was able to achieve 99% accuracy on training and validation dataset within a minute after 3 epochs when trained on a regular i7 CPU.

What lies ahead?

Intent classification and named entity recognition are the two most important parts while making a goal oriented chatbot.

There are many open source python packages for making a chatbot, Rasa is one of them. The cool thing about Rasa is that every part of the stack is fully customizable and easily interchangeable. Although Rasa has an excellent built in support for intent classification task but we can also specify our own model for the task, check Processing Pipeline for more information on it.

Resources

Using pre-trained word embeddings in a Keras model

Convolutional Neural Networks for Sentence Classification

A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].