Connect with us

AI

Automating WhatsApp with NLP: Complete guide

Published

on


Source
subhasish_basak

We all know that coding is a superpower and can achieve numerous things with it. In this article we briefly review one of its application by ‘Building a chat bot using python’. Well, actually not only a chat bot but you can do a lot of cool stuffs with it. All you need is basic knowledge in python programming. P.S. This tutorial is only for educational purpose to demonstrate another application of Natural Language Processing (NLP) in Machine Learning using Python. Don’t blame us if your friends block you on whatsapp 😜.

We started this as a summer project during the quarantine period and now the source code along with a downloadable version of a pre release named ChatBot v0.1.0-alpha is available on GitHub. For training the bot we have used an NLP model based on word-2-vec and a Bayesian approach for updating the probabilities, originally developed by my roommate Aritra Banerjee a.k.a Arolive (find it on Arolive’s GitHub). The bot is still under development and it needs to learn a lot, but it can do the following things right now:

  • Sending Automated replies on behalf of you — Let the ChatBot reply to your chats when you are too busy. Our algorithm will train the ChatBot to talk just like you do (both user & chat specific 😎 ).
  • Sending Scheduled text messages to multiple chats — Never forget to wish your loved ones on their birthdays/anniversaries. Let the ChatBot send a scheduled text.
  • Sending text messages iteratively — The ChatBot becomes handy in case if you wish to apologize to someone by sending ‘I am sorry’ a 100 times (couldn’t think of a better example than this! 😅)
  • Clone a bot — You can create a customized ChatBot with a secondary account and chat with it, train it to talk like anyone!!
  • Tell us if you can think of something else to do! After all necessity is the mother of all inventions.
sending recursive messages

Now if you are interested in the technical part and the ML implementation here is the thing you are searching for. We summarize the steps as follows:

Pr-requisites we have considered

Platform : Python 3.6
Packages/dependencies : Selenium 3.141.0 , beautifulsoup4 4.7.1, numpy 1.18.2, gensim 3.7.3, scipy 1.1.0 etc.
OS : linux/windows (simply because neither of us use a Mac)

Step 1 : Configuring the setup

First you need a browser. Our ChatBot works on both Firefox and Chromium (Firefox is recommended since Chromium does not seem to support BMP file emojis). Once you decide upon the browser you need to install the web driver for that,
For Firefox : Download Here
For Chromium : Download Here
Note that you will be needing the path of this web driver for accessing the browser using python. Once you have the web driver and browser ready, the Selenium package in python bridges the gap between the your local machine’s compiler and the website you wish to work on (for our case we will be using WhatsApp Web).

source : google.com/images

Step 2 : Building the NLP model

The main purpose of this article is to give the reader an overall idea about our proposed Natural Language Processing model. Our algorithm works on the following structure:

  • The problem : Suppose we have a text corpus involving chats of 2 individuals U₁ and U₂. Further we want to automate the replies from U₂ corresponding to a particular text message(s) from U₁.
  • Data processing : Let T₁ : {T₁₀, T₁₁, .. ,T₁ₘ} be m text messages from U₁ which is followed by n text messages T₂ : {T₂₀, T₂₁, .. ,T₂ₙ} from U₂. Our proposed algorithm combines the individual texts messages and establishes a One-2-One mapping between T₁ and T₂. This step also includes some pre-processing of the raw text corpus (for e.g. converting into lowercase, removing digits, removing blank spaces, removing selective punctuation etc). After processing we have One-2-One mapped set of strings, ready to feed the model.

1. Chatbot Best Practices for designing a Conversational Experience

2. PythonBot

3. Chatbot software: Dominate the market (The Ultimate Guide)

4. How To Grow Your Business With The Help Of Artificial Intelligence

The main challenge with the model as well as the most interesting part was to work with a corpus that includes both English and local languages (Bengali in our case), where essentially the context of a word plays a major role. Hence, to obtain the vectorized string embedding, we have used the standard word-2-vec model, in order to take the semantics into consideration as well. Empirically the best results were obtained with window size 5.

  • Predictive model : Let V₁ & V₂ be the corresponding word-2-vec embedding for T₁ & T₂. Also let mapper(.) defines the 1–1 function which maps V₁ to corresponding V₂, more precisely for a given input vector V₁ corresponding to U₁, mapper(.) returns the unique V₂ corresponding to U₂. Now for a new test input T₁* from U₁ we predict the corresponding T₂* as,

V₂* = mapper(argmin {cosine-distance (V₁*, V₁)})

Note that, the above algorithm ensures that the predicted reply should have occurred at least once in the corpus, and in this way it eliminates the chance of meaningless replies.

Although the actual implementation includes a Bayesian approach of updating the weights for each string embedding. We start with trivial prior assumption of equally probable replies of the texts, in other words each vector Vᵢ has a probability of 1/count(Vᵢ) of occurring in the corpus. Next each Vᵢ is multiplied with an appropriate weight given by α/(α + p(Vᵢ)) to emphasize the conditional posterior distribution of the texts over the whole corpus. The hyper-parameter value α is set to its empirically optimal choice 0.001. The function p() computes the empirical probabilities of occurrences of the text replies.

Step 3 : Lets code it

The above algorithm is pretty straight forward to code, thanks to Arolive for this (Take a peek at Arolive’s GitHub repository). The ChatBot is built with a thin wrapper around this model which is easily customizable.

Apart from the algorithm the website scrapping part requires a little familiarity with HTML and our life is made easy when we have “beautiful” parsers (beautifulsoup4 4.7.1). Note that scrapping a webpage is not always a legal act under certain terms and one should be careful about its uses (but I guess everything for fair in educational purposes 😛 ).

Future work & references:

  • Till now the launcher function whatsapp.py partially has the above mentioned functionalities only, but there are numerous things that can be done with. Feel free to fork the repository and continue this project. Also we have listed several issues which can be good starting point for potential future developments.
  • Please don’t hesitate if you have any comments/suggestions 😃 specially on the NLP model. Feel free to share your thoughts/views either by creating a pull request on the GitHub repository or contact me (homepage).

Source: https://chatbotslife.com/automating-whatsapp-with-nlp-complete-guide-1d0dfb180557?source=rss—-a49517e4c30b—4

AI

How does it know?! Some beginner chatbot tech for newbies.

Published

on

Wouter S. Sligter

Most people will know by now what a chatbot or conversational AI is. But how does one design and build an intelligent chatbot? Let’s investigate some essential concepts in bot design: intents, context, flows and pages.

I like using Google’s Dialogflow platform for my intelligent assistants. Dialogflow has a very accurate NLP engine at a cost structure that is extremely competitive. In Dialogflow there are roughly two ways to build the bot tech. One is through intents and context, the other is by means of flows and pages. Both of these design approaches have their own version of Dialogflow: “ES” and “CX”.

Dialogflow ES is the older version of the Dialogflow platform which works with intents, context and entities. Slot filling and fulfillment also help manage the conversation flow. Here are Google’s docs on these concepts: https://cloud.google.com/dialogflow/es/docs/concepts

Context is what distinguishes ES from CX. It’s a way to understand where the conversation is headed. Here’s a diagram that may help understand how context works. Each phrase that you type triggers an intent in Dialogflow. Each response by the bot happens after your message has triggered the most likely intent. It’s Dialogflow’s NLP engine that decides which intent best matches your message.

Wouter Sligter, 2020

What’s funny is that even though you typed ‘yes’ in exactly the same way twice, the bot gave you different answers. There are two intents that have been programmed to respond to ‘yes’, but only one of them is selected. This is how we control the flow of a conversation by using context in Dialogflow ES.

Unfortunately the way we program context into a bot on Dialogflow ES is not supported by any visual tools like the diagram above. Instead we need to type this context in each intent without seeing the connection to other intents. This makes the creation of complex bots quite tedious and that’s why we map out the design of our bots in other tools before we start building in ES.

The newer Dialogflow CX allows for a more advanced way of managing the conversation. By adding flows and pages as additional control tools we can now visualize and control conversations easily within the CX platform.

source: https://cloud.google.com/dialogflow/cx/docs/basics

This entire diagram is a ‘flow’ and the blue blocks are ‘pages’. This visualization shows how we create bots in Dialogflow CX. It’s immediately clear how the different pages are related and how the user will move between parts of the conversation. Visuals like this are completely absent in Dialogflow ES.

It then makes sense to use different flows for different conversation paths. A possible distinction in flows might be “ordering” (as seen here), “FAQs” and “promotions”. Structuring bots through flows and pages is a great way to handle complex bots and the visual UI in CX makes it even better.

At the time of writing (October 2020) Dialogflow CX only supports English NLP and its pricing model is surprisingly steep compared to ES. But bots are becoming critical tech for an increasing number of companies and the cost reductions and quality of conversations are enormous. Building and managing bots is in many cases an ongoing task rather than a single, rounded-off project. For these reasons it makes total sense to invest in a tool that can handle increasing complexity in an easy-to-use UI such as Dialogflow CX.

This article aims to give insight into the tech behind bot creation and Dialogflow is used merely as an example. To understand how I can help you build or manage your conversational assistant on the platform of your choice, please contact me on LinkedIn.

Source: https://chatbotslife.com/how-does-it-know-some-beginner-chatbot-tech-for-newbies-fa75ff59651f?source=rss—-a49517e4c30b—4

Continue Reading

AI

Who is chatbot Eliza?

Between 1964 and 1966 Eliza was born, one of the very first conversational agents. Discover the whole story.

Published

on


Frédéric Pierron

Between 1964 and 1966 Eliza was born, one of the very first conversational agents. Its creator, Joseph Weizenbaum was a researcher at the famous Artificial Intelligence Laboratory of the MIT (Massachusetts Institute of Technology). His goal was to enable a conversation between a computer and a human user. More precisely, the program simulates a conversation with a Rogérian psychoanalyst, whose method consists in reformulating the patient’s words to let him explore his thoughts himself.

Joseph Weizenbaum (Professor emeritus of computer science at MIT). Location: Balcony of his apartment in Berlin, Germany. By Ulrich Hansen, Germany (Journalist) / Wikipedia.

The program was rather rudimentary at the time. It consists in recognizing key words or expressions and displaying in return questions constructed from these key words. When the program does not have an answer available, it displays a “I understand” that is quite effective, albeit laconic.

Weizenbaum explains that his primary intention was to show the superficiality of communication between a human and a machine. He was very surprised when he realized that many users were getting caught up in the game, completely forgetting that the program was without real intelligence and devoid of any feelings and emotions. He even said that his secretary would discreetly consult Eliza to solve his personal problems, forcing the researcher to unplug the program.

Conversing with a computer thinking it is a human being is one of the criteria of Turing’s famous test. Artificial intelligence is said to exist when a human cannot discern whether or not the interlocutor is human. Eliza, in this sense, passes the test brilliantly according to its users.
Eliza thus opened the way (or the voice!) to what has been called chatbots, an abbreviation of chatterbot, itself an abbreviation of chatter robot, literally “talking robot”.

Source: https://chatbotslife.com/who-is-chatbot-eliza-bfeef79df804?source=rss—-a49517e4c30b—4

Continue Reading

AI

FermiNet: Quantum Physics and Chemistry from First Principles

Weve developed a new neural network architecture, the Fermionic Neural Network or FermiNet, which is well-suited to modeling the quantum state of large collections of electrons, the fundamental building blocks of chemical bonds.

Published

on

Unfortunately, 0.5% error still isn’t enough to be useful to the working chemist. The energy in molecular bonds is just a tiny fraction of the total energy of a system, and correctly predicting whether a molecule is stable can often depend on just 0.001% of the total energy of a system, or about 0.2% of the remaining “correlation” energy. For instance, while the total energy of the electrons in a butadiene molecule is almost 100,000 kilocalories per mole, the difference in energy between different possible shapes of the molecule is just 1 kilocalorie per mole. That means that if you want to correctly predict butadiene’s natural shape, then the same level of precision is needed as measuring the width of a football field down to the millimeter.

With the advent of digital computing after World War II, scientists developed a whole menagerie of computational methods that went beyond this mean field description of electrons. While these methods come in a bewildering alphabet soup of abbreviations, they all generally fall somewhere on an axis that trades off accuracy with efficiency. At one extreme, there are methods that are essentially exact, but scale worse than exponentially with the number of electrons, making them impractical for all but the smallest molecules. At the other extreme are methods that scale linearly, but are not very accurate. These computational methods have had an enormous impact on the practice of chemistry – the 1998 Nobel Prize in chemistry was awarded to the originators of many of these algorithms.

Fermionic Neural Networks

Despite the breadth of existing computational quantum mechanical tools, we felt a new method was needed to address the problem of efficient representation. There’s a reason that the largest quantum chemical calculations only run into the tens of thousands of electrons for even the most approximate methods, while classical chemical calculation techniques like molecular dynamics can handle millions of atoms. The state of a classical system can be described easily – we just have to track the position and momentum of each particle. Representing the state of a quantum system is far more challenging. A probability has to be assigned to every possible configuration of electron positions. This is encoded in the wavefunction, which assigns a positive or negative number to every configuration of electrons, and the wavefunction squared gives the probability of finding the system in that configuration. The space of all possible configurations is enormous – if you tried to represent it as a grid with 100 points along each dimension, then the number of possible electron configurations for the silicon atom would be larger than the number of atoms in the universe!

This is exactly where we thought deep neural networks could help. In the last several years, there have been huge advances in representing complex, high-dimensional probability distributions with neural networks. We now know how to train these networks efficiently and scalably. We surmised that, given these networks have already proven their mettle at fitting high-dimensional functions in artificial intelligence problems, maybe they could be used to represent quantum wavefunctions as well. We were not the first people to think of this – researchers such as Giuseppe Carleo and Matthias Troyer and others have shown how modern deep learning could be used for solving idealised quantum problems. We wanted to use deep neural networks to tackle more realistic problems in chemistry and condensed matter physics, and that meant including electrons in our calculations.

There is just one wrinkle when dealing with electrons. Electrons must obey the Pauli exclusion principle, which means that they can’t be in the same space at the same time. This is because electrons are a type of particle known as fermions, which include the building blocks of most matter – protons, neutrons, quarks, neutrinos, etc. Their wavefunction must be antisymmetric – if you swap the position of two electrons, the wavefunction gets multiplied by -1. That means that if two electrons are on top of each other, the wavefunction (and the probability of that configuration) will be zero.

This meant we had to develop a new type of neural network that was antisymmetric with respect to its inputs, which we have dubbed the Fermionic Neural Network, or FermiNet. In most quantum chemistry methods, antisymmetry is introduced using a function called the determinant. The determinant of a matrix has the property that if you swap two rows, the output gets multiplied by -1, just like a wavefunction for fermions. So you can take a bunch of single-electron functions, evaluate them for every electron in your system, and pack all of the results into one matrix. The determinant of that matrix is then a properly antisymmetric wavefunction. The major limitation of this approach is that the resulting function – known as a Slater determinant – is not very general. Wavefunctions of real systems are usually far more complicated. The typical way to improve on this is to take a large linear combination of Slater determinants – sometimes millions or more – and add some simple corrections based on pairs of electrons. Even then, this may not be enough to accurately compute energies.

Source: https://deepmind.com/blog/article/FermiNet

Continue Reading
AI7 hours ago

How does it know?! Some beginner chatbot tech for newbies.

AI7 hours ago

Who is chatbot Eliza?

AI21 hours ago

FermiNet: Quantum Physics and Chemistry from First Principles

AI1 day ago

How to take S3 backups with DejaDup on Ubuntu 20.10

AI2 days ago

How banks and finance enterprises can strengthen their support with AI-powered customer service…

AI2 days ago

GBoard Introducing Voice — Smooth Texting and Typing

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

AI3 days ago

Automatically detecting personal protective equipment on persons in images using Amazon Rekognition

Trending