5 Minute ML: Chatbot (QnA) Demystified

, ,

From a Natural Language Processing perspective, a chatbot normally consists of many parts — small talk, QnA (question and answer — included intent prediction and entity extraction), context handling (user, session etc.), question completion, personalization, sentiment analysis, and so on. Not every chatbot needs all the above-mentioned capabilities. You can have just small talk and QnA and create a chatbot or assemble small talk, QnA and personalization and handle most of the user’s queries. But every chatbot needs QnA.

In this article, we focus on only the Q part of QnA. This is the most complex part of any chatbot framework and needs expertise in Machine Learning, Natural Language Processing and in some cases Deep Learning. Intent Prediction and Entity Extraction are 2 major components of the Q part, which helps the system understand the user query in terms of the answer repository. Answer repository is the domain for which we have built the chatbot. The answer repository can be as simple as a set of FAQs or an excel file or as complex as a database, a SAP system, or a knowledge base.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Build a Fully Functioning App Leveraging Machine Learning with TensorFlow.js

, ,

TensorFlow.js is a JavaScript library for training and deploying Machine Learning (ML) models in the browser (client-side) and on Node.js (server-side). In this article, I want to describe my experience in building an App (that I recently published on Google Play Store) with this javascript ML library.

However, instead of just going straight into how I built this app using TensorFlow.js, I want to first describe the conditions/needs that led to this choice. I also want to touch a little bit on some other approaches that I realized could be possible that you can take to build an App leveraging machine learning. Finally, I want to leave behind some lessons I learned through this experience and would love your thoughts if you have been experimenting with ML in Apps.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Ethical AI: Lessons from Google AI Principles

, ,

Is your organization using AI/machine learning for many of its products, or planning to use AI models extensively for upcoming products? Do you have a set of AI guiding principles in place for stakeholders such as product managers, data scientists, and machine learning researchers to make sure that safe and unbiased AI is used for developing AI-based solutions? Are you planning to create AI guiding principles for other AI stakeholders, including business stakeholders, customers, and partners?

If the answer to the above questions is not "yes," you should start thinking about laying down AI guiding principles, sooner than later, to help everyone from the executive team to product management to data scientists plan, build, test, deploy, and govern your AI-based products. The rapidly growing capabilities of AI-based systems have started inviting questions from business stakeholders (including customers and partners) to provide details on the impact, governance, ethics, and accountability of AI-based products integrated into various business processes and workflows. No longer can a company afford to hide some of the above details in light of IP-related or privacy concerns. 


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Python Logic Programming With Example

, ,

What is Logic Programming?

Logic programming is a programming paradigm that sees computation as automatic reasoning over a database of knowledge made of facts and rules. It is a way of programming and is based on formal logic. A program in such a language is a set of sentences, in logical form, one that expresses facts and rules about a problem domain. Among others, Datalog is one such major logic programming language family.

Structure

Let’s talk about facts and rules. Facts are true statements — say, Bucharest is the capital of Romania. Rules are constraints that lead us to conclusions about the problem domain. These are logical clauses that express facts. We use the following syntax to write a rule (as a clause):


Source de l’article sur DZONE (AI)

/0 Commentaires/par

AI and Music: Noteworthy?

, ,

There are an increasing number of organizations developing and/or using music composed in part or in full by AI technologies. In the beginning, many of those efforts were academic in nature, but a growing number of groups are attempting to make a business model of composing music. And while there are more people doing it now than there were a couple decades ago, the idea of computer-composed music is reasonably old. One of the first computer compositions I’m aware of was in 1957.

The majority of these systems are structured just as you would expect: a large collection of compositions representing a genre or an artist are used as training data, which create some sort of generative/predictive model. In the very earliest approaches, simple Markov chains were derived from the compositions.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Using AI To Improve The PubMed Interface

, ,

Most efforts to utilize AI and Machine Learning to help us digest the research literature have revolved around supporting people as they attempt to "drink from the fire hose" of research coming out. With several thousand new papers every day, it’s a much-needed level of support.

This isn’t the only use case being explored, however, as a recent paper was published in PLOS Biology highlights. The paper describes the use of AI to help users as they search the PubMed database for research.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Can AI-Driven Test Automation Enhance Continuous Delivery?

, ,

Continuous Delivery is no longer a value-enhancing strategy, it is a much-needed approach in software development and release lifecycle. It has substantially changed the way enterprises test and launch their applications in a volatile consumer ecosystem. The demand for Intelligent Applications is on the rise. In fact, it is predicted that almost all the applications will be delivered with embedded intelligence. It practically implies that these applications will have the capability to scrutinize historical and real-time data to deliver customized experiences and results to the end-users by leveraging Machine Learning technologies. Hence, testing these applications will need a relevant Test Automation strategy and a Continuous Delivery plan.

In the current Digital ecosystem, consumers are swarmed by chatbots and virtual assistants across diverse websites and applications. These features are not only automating basic activities, but are also delivering enhanced and personalized experiences. At a recent Google conference, CEO Sundar Pichai opened the event by stating, "We’re moving from a mobile-first to an AI-first world." Hence, due to growing business mandate and evolving consumer preferences, the need to build such robust applications is increasing by the day.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Is AI Going to Transform the Design Industry?

, ,

AI has emerged as the mainstream trend in various industries. AI might excite us and terrify us at the same time. AI is widely unknown and experts are researching day in and day out to discover how AI will affect the design industry in the upcoming days.

Since AI has become apparent in a large number of areas including medical, entertainment, sports, and more, the design industry is no exception. Intense debates are taking place between the designers and developers worldwide about how AI would influence the web design and development. Machine Learning, Virtual Reality (VR), Augmented Reality (AR), Mixed Reality (MR), and Deep Learning are expected to mark major footsteps in the design and development industry.


Source de l’article sur DZONE (AI)

/0 Commentaires/par

Microsoft Chatbot Framework: Up and Running

, ,

Some time ago (think early to mid-nineties), I used to run a BBS. One Christmas, I logged onto another BBS based in Manchester, and they had a "Santa Chat."  I tried it for a while and was so impressed by it that I decided to write my own; it was basically the gift that kept giving. You put this thing on your BBS (basically an Eliza clone) and it records the responses of the unsuspecting users to a text file (or log).

These days there are laws against recording such things, but those were simpler times, and once they realized the joke, everyone was happy, and life went on (albeit at 14.4k bps).


Source de l’article sur DZONE (AI)

/0 Commentaires/par

MIT Team Develops AI-Assisted Image Editing

, ,

It’s increasingly appreciated that AI can play a crucial role in supporting the work that we do, and a good example of how this will play out comes via a recent study from MIT CSAIL that describes how AI can help support image and multimedia editing.

The editing of images is now not only a major part of publishing and advertising, but increasingly of film making, and a big part of the process is "compositing," which is the merging of foreground and background images so that actors are placed on top of items, such as planes or planets. Making this look realistic is very hard, however.


Source de l’article sur DZONE (AI)

/0 Commentaires/par