Chatbots: From Alan Turing to our decade.

Photo by Austin Distel on Unsplash

What are chatbots?

Chatbots are “online human-computer dialog system[s] with natural language”. In simple words, chatbots is a virtual person who can effectively talk to any human being using interactive textual skills.

The main idea of chatbots started from Alan Turing, who asked “Can machine think?” in 1950. Let’s remember an example of Turing in one section of “Computing Machinery and Intelligence”. In this example Turing simulated what the test might look like when human asking questions and an imagined intelligent computer responding.

Q: Please write me a sonnet on the subject of the Forth Bridge.

A: Count me out on this one. I never could write poetry.

Q: Add 34957 to 70764.

A: (Pause about 30 seconds and then give as answer) 105621.

Q: Do you play chess?

A: Yes.

Q: I have K at my K1, and no other pieces. You have only K at K6 and R at R1. It is your move. What do you play?

A: (After a pause of 15 seconds) R-R8 mate.

Τheir evolution of chatbots over the years

Since Turing, chatbot technology has improved with advances in natural language processing and machine learning. Nowadays, many large firms have adopted the chatbot technology, like Facebook, Kik, Slack, Telegram etc.

Moderns chatbots include Amazon’s Echo and Alexa, Apple’s Siri, and Microsoft’s Contana. Theses chatbots’ architectures and retrieval processes provide advanced “information retrieval” processes, in which responses are generated based on analysis of the results of web searches. Algorithms, like Seq2Seq, are used to encode and decode inputs into responses and it is referred as the best practice.

Trending Bot Articles:

1. How Conversational AI can Automate Customer Service

2. Automated vs Live Chats: What will the Future of Customer Service Look Like?

3. Chatbots As Medical Assistants In COVID-19 Pandemic

4. Chatbot Vs. Intelligent Virtual Assistant — What’s the difference & Why Care?

Chatbot Programming Challenges

There are many challenges which are associated with chatbots. Some of them are the following:

Natural language processing (NLP)

The first challenge of the chatbot is to handle NLP issue. The syntax of a question can create problems to chatbot. For example, if you ask “What’s the weather”, you can take an answer. However, if you ask “Could you tell about the weather?”, you can take another answer, which will not be the proper. Large companies like Facebook and Apple take care to these part, for more accurate results.

Machine Learning

Machine Learning is another aspect of the Chatbot design and development. Our computer systems should able to learn the correct response should be which can be achieved with efficient programming with AI concepts.

Paper References:

Cahn, J. (2017). CHATBOT: Architecture, design, & development. University of Pennsylvania School of Engineering and Applied Science Department of Computer and Information Science.

A. M. Rahman, A. A. Mamun and A. Islam, “Programming challenges of chatbot: Current and future prospective,” 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), 2017, pp. 75–78, doi: 10.1109/R10-HTC.2017.8288910.

Journal References

Untold History of AI: Why Alan Turing Wanted AI Agents to Make Mistakes

Don’t forget to give us your 👏 !


Chatbots: From Alan Turing to our decade. was originally published in Chatbots Life on Medium, where people are continuing the conversation by highlighting and responding to this story.


Posted

in

by

Tags: