An open source library for deep learning end-to-end dialog systems and chatbots.
-
Updated
Jun 17, 2020 - Python
An open source library for deep learning end-to-end dialog systems and chatbots.
building a chinese dialogue system based on the newest version of rasa(基于最新版本rasa搭建的对话系统)
State of the Art results in Intent Classification using Sematic Hashing for three datasets: AskUbuntu, Chatbot and WebApplication.
multi_task_NLP is a utility toolkit enabling NLP developers to easily train and infer a single model for multiple tasks.
A neural network intent parser
CNN for intent classification task in a Chatbot
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
Labelling Sequential Data in Natural Language Processing with R - using CRFsuite
Natural language understanding library for chatbots with intent recognition and entity extraction.
Is your feature request related to a problem? Please describe.
To use google geolocation api, User has to fill the credit details. Instead, we can use opensource geocoding api available.
Describe the solution you'd like
We can use alternate geocoding api available to get the same feature.
Import the Wiki from a backup.
Ipython Notebooks for solving problems like classification, segmentation, generation using latest Deep learning algorithms on different publicly available text and image data-sets.
Annabelle the noob. An experimental, incomplete(at present) chatbot.
Using Tensorflow to train a slot-filling & intent joint model
reference pytorch code for intent classification
Java tools to do natural language processing like NER and intent classification on short sentences
The Ovation Framework for Conversational Intelligence
Towards an Understanding of Entity-Oriented Search Intents - ECIR'18
Intent classification using a variety of deep learning models
reflect's backend - determine intent validity
A chat bot designed to answer FAQs of a specific subject using Rasa-NLU (Natural Language API)
基于 rasa 1.x 版本搭建的英文天气查询 demo | A simple & micro English Weatherbot based on rasa framework
Intent classification and entity extraction with natural language understanding using RASA-NLU.
An Open-Source Package for Universal Extraction (UE)
Convokit is a python based contextual chatbot framework
Add a description, image, and links to the intent-classification topic page so that developers can more easily learn about it.
To associate your repository with the intent-classification topic, visit your repo's landing page and select "manage topics."
I have some values in slots that are surrounded by curly braces and are meant to be returned as is. Instead, the trailing brace is being stripped. "${website}" becomes "${website". I have training examples where the whole "${website}" is included. Is there a way to change this behavior?