Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

A Study on the Best NLP Tools for Conversational Bot Makers

DZone's Guide to

A Study on the Best NLP Tools for Conversational Bot Makers

There are several tools available in the market for building chatbots, including Dialogflow, Wit.ai, Amazon Lex, LUIS, and Watson. This article discusses these tools.

· AI Zone ·
Free Resource

EdgeVerve’s Business Applications built on AI platform Infosys Nia™ enables your enterprise to manage specific business areas and make the move from a deterministic to cognitive approach.

Chatbots: A term which is familiar to the layman. We can see and experience the usage of chatbots in our daily lives. With the advent of technology, changes in consumer’s behavior increase along with expectations. Through technological expansion, chatbots and intelligent assistants are redefining the user engagement and brand experiences.

It's better to start with a quote from Ted Livingston, Founder and CEO of Kik:

Chat apps will come to be thought of as the new browsers; bots will be the new websites. This is the beginning of a new internet.

What Are Chatbots?

In simple words, a chatbot is a software chunk that helps chat with things to get done or to be entertained. It is a technology that aids the human to converse with computers in their own language using a graphical interface. Chatbots tend to mimic humans in performing any tasks or conversing.

With the technological revolution, chatbots evolved in 1950 with Alan Turing’s intelligent machine. Many artificial intelligent systems emerged in the course of time following Turing’s intelligent machine.

Importance of Chatbots

Chatbots are gaining popularity in the implementation of real-world applications. They can cater the customer experience by providing customer support and service, product recommendations and suggestions, and engaging customers with appealing marketing campaigns.

Chatbots can function as a lawyer, teacher, doctor, personal stylist, toy, and even as a companion, thus enriching our life.

Building a Chatbot

A successful chatbot is human-like and provides valuable features that help users. For building a chatbot, we have to identify its function and purpose and then corresponding sector for which we are using it.

Tools for Building Chatbots

We now have a basic idea about chatbots and their importance. Now, the question arises: Where and how can I build a chatbots?

There are several tools available in the market for building chatbots, including Dialogflow, Wit.ai, Amazon Lex, LUIS, Watson, and so on.

The following section discusses these tools.

1. DialogFlow (Api.ai)

Api.ai is now known as DialogFlow. It was acquired by Google in 2016. This platform connects with users on Google Assistant and other messaging apps and devices.

Here is an excerpt from the CEO of DialogFlow at ProductHunt about the characteristic features of DialogFlow.

DialogFlow uses intents, entities, actions with parameters, contexts, and speech to text and text to speech capabilities, along with machine learning that works silently and trains your model. DialogFlow has built-in knowledge on topics like casual talks, weather, and wisdom. It means we don’t have to train the agent for these intents. DialogFlow returns the output as JSON data.

  • Programming languages/apps/integration: SDKs, Android, iOS, Cordova, JavaScript, HTML, Node.js, .NET, Unity, Xamarin, C++, Python, Ruby, PHP (community supported), Epson Moverio, Botkit, Java; built-in integration with Google Assistant, Facebook Messenger, and Slack.
  • Platform: Google Assistant and other messaging platforms.
  • Supported languages: Brazilian Portuguese, Chinese (Cantonese), Chinese (Simplified), Chinese (Traditional), English, Dutch, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish, and Ukrainian.
  • Pricing: Free.
  • Limit for API calls: Unlimited.
  • Third-party integration: Allowed for different messengers and some additional services.
  • Suitable for: Middle-level B2C bots, Virtual Assistants, and MVPs.

2. Wit.ai

Wit.ai was acquired by Facebook. It is a SaaS platform that makes it easy for developers to build a chatbot for their app or device. It can be used in platforms that learn new commands semantically to those input by the developer.

  • Programming languages/apps/integrations: Node.js client, Python client, Ruby client; on other platforms, HTTP API.
  • Platform: Applications and devices that you can talk to or text.
  • Supported languages: Albanian, Arabic, Azerbaijani, Bengali, Bosnian, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Georgian, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Korean, Latin, Lithuanian, Macedonian, Malay, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, and Vietnamese.
  • Pricing: Free.
  • Limit for API calls: Unlimited.
  • Third-party integration: Doesn’t support third-party integration tools.
  • Suitable for: Simple B2C bots and MVPs.

3. Amazon Lex

Amazon Lex is a service for building chatbots for any application or device using voice and text. Using Amazon Lex, any developer can build conversational chatbots instantly. It is a service provided by Amazon. Amazon Lex provides the advanced deep learning functionalities of automatic speech recognition (ASR) for converting speech to text, along with natural language understanding (NLU) to recognize the intent of the text.

  • Programming languages/apps/integrations: IoS and Android SDKs, Java, JavaScript, Python, CLI, .NET, Ruby, PHP, Go, and C++.
  • Platform: Integration with Facebook, Slack, and Twilio; but if you want to connect to a messaging device/application that isn’t supported, there’s the Amazon Lex API.
  • Supported languages: Amazon Lex is limited to support US English.
  • Pricing: Trial: 1 year; Paid: $0.004 per speech query and $0.00075 per text query
  • Limit for API calls: Trial: 10k speech queries, 5k text queries; Paid: Unlimited
  • Third-party integration: Different messengers, Amazon services, and popular SaaS platforms.
  • Suitable for: Preview mode, just for making an opinion.

4. LUIS

LUIS is an acronym for Language Understanding Intelligent Service. It is the service provided by Microsoft. Luis understands the language of laymen contextually and communicates in the way they speak. It also uses intents and entities. One of the key features of Luis is active learning technology. It offers pre-built domains for things like devices, music, calendars, and so on.

  • Programming languages/apps/integrations: C# SDK, Python SDK, Node JS SDK, and Android SDK.
  • Platform: Facebook, Kik, Slack, Telegram, Twilio, Microsoft Teams, Skype, GroupMe, Web Chat, Email, and Direct Line.
  • Supported languages: English, French, Italian, German, Spanish, Brazilian Portuguese, Japanese, Korean, and Chinese.
  • Pricing: LUIS API — Free: 10,000 transactions free per month; LUIS API — Basic: Up to 10 transactions per second; $0.75 per 1,000 transactions.
  • Limit for API calls : Free: 10,000 queries per month and five queries per second. Paid: Ten queries per second; $0,75 per 1,000 queries.
  • Third-party integration: Microsoft Azure and different messengers via Bot Framework.
  • Suitable for: Cortana functionality, IoT applications and virtual assistant apps, and bots integrated to enterprise software.

5. IBM Watson

Watson is an AI platform provided by IBM. It can understand all forms of data, interact with people, and learn from that interaction. IBM had moved the technology of Watson into the cloud and released its API allowing the user to make conversational bots. It is built on neural networks. The main components are intents, entities, and dialog.

  • Programming languages/apps/integrations: Node SDK, Java SDK, Python SDK, iOS SDK, and Unity SDK.
  • Platform: Any messaging platform supporting speech, images, and text.
  • Supported languages: English and Japanese.
  • Pricing: Lite, Standard, and Premium plans are available for Watson. Lite: 1,000 queries per month; Standard: $0.0025 per API call; Premium: Price as per request.
  • Limit for API calls: Lite: 1,000 API queries per month; Standard: Unlimited API queries per month, up to 20 workspaces, up to 2,000 intents; Premium: Unlimited.
  • Third-party integration: IBM Services
  • Suitable for: Virtual assistants and bots that integrate with IBM services.

Popularity of NLP Tools

We are witnessing a huge demand for the growth of chatbots. Currently, a large number of platforms are available for making chatbots. The tools discussed above are backed by tech giants. We could say they all maintain a certain standard. The below figure shows the Google trends in the conversational interfaces.

Wrapping Up

To create a chatbot for your business, a variety of NLP tools are available to you. The choice of tool depends on your requirements and needs, integration needed, and technology preference. There are many more platforms to explore. We have given a glimpse of few frameworks and tools that would be useful for building chatbots. With the pace of progress and interest in conversational interfaces, new tools may soon arise in the market.

Adopting a digital strategy is just the beginning. For enterprise-wide digital transformation to truly take effect, you need an infrastructure that’s #BuiltOnAI. Click here to learn more.

Topics:
ai ,nlp ,chatbots ,bot development

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}