Here is my Senior Design Project that I implemented to graduate from Computer Engineering.

Overview

rasa-travel-chatbot

Ekran Resmi 2021-06-20 15 44 14

Here is my Senior Design Project that I implemented to graduate from Computer Engineering. It is a chatbot made in RASA and helps the user to plan their vacation in the Turkish language. In order to plan the user's vacation, it provides reservations by asking various questions for hotel, flight, or event.

How to Run the Project?

  1. Create a virtual environment of python 3.6 or greater.
  2. Navigate to the rasa directory. Run the command: rasa train
  3. After the model is trained, launch the rasa core server: rasa run -m models --enable-api
  4. Launch the rasa actions server in another terminal: rasa run actions
  5. Navigate to the chatbot/backend. Run the command: python route.py
  6. Launch the frontend on the local python http server under the interface directory: python -m http.server

Interface

Here is an example conversation for booking an event in Turkish.

Ekran Resmi 2021-06-20 15 00 44

In this figure, the chatbot is trying to learn which event the user wants to go to after the greeting.

Ekran Resmi 2021-06-20 15 00 57

After that the chatbot asks for how many tickets the user wants and tries to make the reservation by asking for an e-mail.

Ekran Resmi 2021-06-20 15 01 06

Finally, the chatbot tells the user how many tickets it has bought and sent to which e-mail address and asks if the user wants to take another action. If the user says no, chatbot finishes the conversation by saying goodbye.

Turkish Dataset

Due to the small number of chatbots in the Turkish language, Turkish datasets are also less. For this reason, we prepared a Turkish dataset from scratch while doing this project. In order to do this, we translated the English datasets into Turkish using the Google API. In the end, we have 93 intents 29 entities in total, and an average of 7 sentences for each intent.

Ekran Resmi 2021-06-20 15 08 45

RASA

Rasa is an open source python library for constructing conversational software with minimal (or no) initial training data. It consists of two parts: Rasa NLU and Rasa Core. Dialogue management problem can be handled as a classification problem. At each iteration, Rasa Core predicts which action to take from a predefined list. On the other hand, Rasa NLU is a tool for natural language understanding. It combines a number of natural language processing and machine learning libraries in a consistent API.

Ekran Resmi 2021-06-20 15 17 46

First a message is received and passed to Rasa NLU to extract the intent, entities, and the other structured information. Then the conversation state saved in the tracker which receives a notification that a new message has been received. In step 3, the policy receives the current state of the tracker and chooses which action to take next. Then chosen action is logged by the tracker and executed. If the predicted action is not ‘listen’, go back to step 3. After the first step all the remaining steps are performed by Rasa Core.

Ekran Resmi 2021-06-20 15 17 46

Here is an example of intent classification and entity extraction for a possible input sentence that chatbot can receive from user in this project.

Ekran Resmi 2021-06-20 15 45 03

Best Configuration

We used pre-trained language model BERT for our pipeline. We compared three different pipeline configurations: a light configuration, a configuration using ConveRT, and a heavy configuration that included BERT. In each case we’re training a DIETClassifier for combined intent classification and entity recognition for 200 epochs, but in the light configuration we have CountVectorsFeaturizer, which creates bag-of-word representations for each incoming message at word and character levels. In the end, we chose config-light as the configuration of the chatbot.

Results of the Configurations

Ekran Resmi 2021-06-20 15 21 16

Ekran Resmi 2021-06-20 15 21 27

In the images below, there are confusion matrices created by each configuration for intent classification and entity extraction in turn.

config-light:

Ekran Resmi 2021-06-20 15 26 15 Ekran Resmi 2021-06-20 15 26 36 Ekran Resmi 2021-06-20 15 27 25 Ekran Resmi 2021-06-20 15 27 46

config-convert:

Ekran Resmi 2021-06-20 15 30 19 Ekran Resmi 2021-06-20 15 30 30 Ekran Resmi 2021-06-20 15 30 42 Ekran Resmi 2021-06-20 15 30 54

config-heavy:

Ekran Resmi 2021-06-20 15 32 01 Ekran Resmi 2021-06-20 15 32 12 Ekran Resmi 2021-06-20 15 32 22 Ekran Resmi 2021-06-20 15 32 32

Owner
Ezgi Subaşı
Ezgi Subaşı
Create a simple program by applying the use of class

TUGAS PRAKTIKUM 8 💻 Nama : Achmad Mahfud NIM : 312110520 Kelas : TI.21.C5 Perintah : Buat program sederhana dengan mengaplikasikan pengguna

Achmad Mahfud 1 Dec 23, 2021
Calculadora-basica - Calculator with basic operators

Calculadora básica Calculadora com operadores básicos; O programa solicitará a d

Vitor Antoni 2 Apr 26, 2022
Pattern Matching for Python 3.7+ in a simple, yet powerful, extensible manner.

Awesome Pattern Matching (apm) for Python pip install awesome-pattern-matching Simple Powerful Extensible Composable Functional Python 3.7+, PyPy3.7+

Julian Fleischer 97 Nov 03, 2022
Statically typed BNF with semantic actions; A frontend of frontend frameworks; Use your grammar everywhere.

Statically typed BNF with semantic actions; A frontend of frontend frameworks; Use your grammar everywhere.

Taine Zhao 56 Dec 14, 2022
a wordle-solver written in python

Wordle Solver Overview This is yet another wordle solver. It is built with the word list of the official wordle website, but it should also work with

Shoubhit Dash 10 Sep 24, 2022
Python implementation of the ASFLIP advection method

This is a python implementation of the ASFLIP advection method . We would like to hear from you if you appreciate this work.

Raymond Yun Fei 133 Nov 13, 2022
A middle-to-high level algorithm book designed with coding interview at heart!

Hands-on Algorithmic Problem Solving A one-stop coding interview prep book! About this book In short, this is a middle-to-high level algorithm book de

Li Yin 1.8k Jan 02, 2023
This repository containing cross-section cut and fill calculations using Python programming language.

cross-section This repository is containing cut and fill calculations for cross-section using Python programming language. This codes is made to calcu

3 Jun 15, 2022
Small pip update helpers.

pipdate pipdate is a collection of small pip update helpers. The command pipdate # or python3.9 -m pipdate updates all your pip-installed packages. (O

Nico Schlömer 69 Dec 18, 2022
dynamically create __slots__ objects with less code

slots_factory Factory functions and decorators for creating slot objects Slots are a python construct that allows users to create an object that doesn

Michael Green 2 Sep 07, 2021
App to decide weekly winners in H2H 1 Win (9 Cat)

Fantasy Weekly Winner for H2H 1 Win (9 Cat) Yahoo Fantasy API Read

Sai Atmakuri 1 Dec 31, 2021
🍞 Create dynamic spreadsheets with arbitrary layouts using Python

🍞 tartine What this is Installation Usage example Fetching some data Getting started Adding a header Linking more cells Cell formatting API reference

Max Halford 11 Apr 16, 2022
BlueBorne Dockerized

BlueBorne Dockerized This is the repo to reproduce the BlueBorne kill-chain on Dockerized Android as described here, to fully understand the code you

SecSI 5 Sep 14, 2022
🌲 Um simples criador de arvore de items feito em Python para o Prompt 🐍

Esse projeto foi feito em Python com, intuito de fortificar meu aprendizado de programação. Sobre • Tecnologias • Pré Requisitos • Licença • Autor 📄

Kawan Henrique 1 Aug 02, 2021
Autogenerador tonto de paquetes para ROSCPP

Autogenerador tonto de paquetes para ROSCPP Autogenerador de paquetes que usan C++ en ROS. Por ahora tiene las siguientes capacidades: Permite crear p

1 Nov 26, 2021
A (hopefully) considerably copious collection of classical cipher crackers

ClassicalCipherCracker A (hopefully) considerably copious collection of classical cipher crackers Written in Python3 (and run with PyPy) TODOs Write a

Stanley Zhong 2 Feb 22, 2022
A simply dashboard to view commodities position data based on CFTC reports

commodities-dashboard A simply dashboard to view commodities position data based on CFTC reports This is a python project using Dash and plotly to con

71 Dec 19, 2022
A step-by-step tutorial for how to work with some of the most basic features of Nav2 using a Jupyter Notebook in a warehouse environment to create a basic application.

This project has a step-by-step tutorial for how to work with some of the most basic features of Nav2 using a Jupyter Notebook in a warehouse environment to create a basic application.

Steve Macenski 49 Dec 22, 2022
SpellingBeeSolver - This program generates solutions to NYT style spelling bee problems.

SpellingBeeSolver This program generates solutions to NYT style spelling bee problems. The initial version of this program is being written in Python

1 Jan 01, 2022
Excel cell checker with python

excel-cell-checker Description This tool checks a given .xlsx file has the struc

Paul Aumann 1 Jan 04, 2022