pbhatia243 / Neural_conversation_models
Licence: apache-2.0
Tensorflow based Neural Conversation Models
Stars: ✭ 192
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Neural conversation models
Leaderboards For Multi Turn Response Selection
Leaderboards, Datasets and Papers for Multi-Turn Response Selection in Retrieval-Based Chatbots
Stars: ✭ 139 (-27.6%)
Mutual labels: chatbots
Rivescript Python
A RiveScript interpreter for Python. RiveScript is a scripting language for chatterbots.
Stars: ✭ 142 (-26.04%)
Mutual labels: chatbots
Hacksby
Description and unofficial implementation of Furby's audio protocol
Stars: ✭ 165 (-14.06%)
Mutual labels: decoding
Rasa
💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
Stars: ✭ 13,219 (+6784.9%)
Mutual labels: chatbots
Voice Overlay Android
🗣 An overlay that gets your user’s voice permission and input as text in a customizable UI
Stars: ✭ 189 (-1.56%)
Mutual labels: chatbots
Chatskills
Run and debug Alexa skills on the command-line. Create bots. Run them in Slack. Run them anywhere!
Stars: ✭ 171 (-10.94%)
Mutual labels: chatbots
Android Quick Response Code
Android QR Code Decoder and Encoder
Stars: ✭ 158 (-17.71%)
Mutual labels: decoding
Rawloader
rust library to extract the raw data and some metadata from digital camera images
Stars: ✭ 153 (-20.31%)
Mutual labels: decoding
Seq2seq chatbot new
基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
Stars: ✭ 144 (-25%)
Mutual labels: beam-search
Java Telegram Bot Tutorial
Java Telegram Bot Tutorial. Feel free to submit issue if you found a mistake.
Stars: ✭ 165 (-14.06%)
Mutual labels: chatbots
Crypto Rnn
Learning the Enigma with Recurrent Neural Networks
Stars: ✭ 139 (-27.6%)
Mutual labels: decoding
Packetserial
An Arduino Library that facilitates packet-based serial communication using COBS or SLIP encoding.
Stars: ✭ 177 (-7.81%)
Mutual labels: decoding
Phpasn1
A PHP library to encode and decode arbitrary ASN.1 structures using ITU-T X.690 encoding rules.
Stars: ✭ 136 (-29.17%)
Mutual labels: decoding
Formam
a package for decode form's values into struct in Go
Stars: ✭ 160 (-16.67%)
Mutual labels: decoding
Neural_Conversation_Models
================================= This implementation contains an extension of seq2seq tutorial for conversation models in Tensorflow:
-
Option to use Beam Search and Beam Size for decoding
-
Currently, it supports
- Simple seq2seq models
- Attention based seq2seq models
-
To get better results use beam search during decoding / inference
Examples of basic model can be found in this paper.
https://arxiv.org/abs/1702.05512
Prerequisites
- Python 2.7 or Python 3.3+
- NLTK
- TensorFlow
Data
Data accepted is in the tsv format where first component is the context and second is the reply
TSV format Ubuntu Dialog Data can be found here
example :-
- What are you doing ? \t Writing seq2seq model .
Usage
To train a model with Ubuntu dataset:
$ python neural_conversation_model.py --train_dir ubuntu/ --en_vocab_size 60000 --size 512 --data_path ubuntu/train.tsv --dev_data ubuntu/valid.tsv --vocab_path ubuntu/60k_vocan.en --attention
To test an existing model:
$ python neural_conversation_model.py --train_dir ubuntu/ --en_vocab_size 60000 --size 512 --data_path ubuntu/train.tsv --dev_data ubuntu/valid.tsv --vocab_path ubuntu/60k_vocan.en --attention --decode --beam_search --beam_size 25
Todo
- Add other state of art neural models.
- Adding layer normalization( in progress )
https://github.com/pbhatia243/tf-layer-norm
Contact
Parminder Bhatia, [email protected]
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].