March Madness Series - V are the champions

In the first two challenges you asked the questions, in the third, we asked the questions. In this challenge, both of us will ask questions to each other.
This is the last in the series of four challenges using IBM Watson Cognitive services to build a Basketball analysis tool analyzing textual material from top sports writers and commentators.

The first three challenges are found here:
https://www.topcoder.com/challenges/30063503
https://www.topcoder.com/challenges/30063887
https://www.topcoder.com/challenges/30064074

Description

In this challenge, you will build a chatbot that will ask and answer questions related to the two teams in the final. The chatbot should use IBM Discovery / NLU services to analyze textual material from top sports writers and commentators to ask and answer questions about the two teams, players, skill and position. The publication that reported this story will be used a reference for the questions if needed.

Your chatbot and the user will ask each other 5 questions. Questions will be limited to these topics - Player name, Team name, skill, position and entities. 

Your chatbot should:

• have a name and introduce itself
• ask the user their name
• keep score and announce the score at the end of the game and declare the winner (this could be of the form ‘Winner chatbot name: 5 Username: 1’ ) 
• invite the user to ask the first question (in other words, the chatbot plays second)
• ask a question that is connected to the user’s question. If the user asks about a player, the chatbot’s question will be about a player and so on.
• the chatbot should not repeat the user’s questions. 

The user will ask questions only about five answer-types viz. Player name, Team name, skill, player position, entities.
 
Some example questions from this link: http://www.espn.in/mens-college-basketball/story/_/id/22993116/why-villanova-terrifying-offense-hard-slow-down

• Which Wildcats player  does ESPN call  the ‘new wrinkle this season’? (A: Omari Spellman ) - about a player
• What  was Villanova’s ‘record-setting avalanche’ against Kansas? (A:3-pointers) - about a skill
• Which team did Villanova defeat in the Elite Eight? (A: Texas Tech) - about a team
• What is the position of Donte DiVincenzo? (A: Guard) - about a position
• What is the River Walk? (A: Geographic feature) - obtained from Entity types

The user will play the game with the chatbot not more than 3 times - so you should try not to repeat the same question every time. The ability of the chatbot to understand or speak in a natural conversation style is not as important as the ability to answer and ask questions. You also do not have to worry about spelling and grammar issues. Avoid score-related questions like ‘How many points did Player A score against Team B’?

A set of documents from which the user will ask questions will be provided in the forum. You are free to select  any set of documents for your questions. 

Requirements

1. Please join the Topcoder Cognitive Community if you have not already, and get an IBM Cloud Account by using this link.
2. A chatbot with a simple user interface that asks and answers 5 questions with the user as described above.
3. A design document on your approach.

Final Submission Guidelines

1. Deploy your application to your own IBM Cloud instance.
2. Upload a .zip containing your source code and a text file called ibm-cloud-deployment.txt.  This .txt file should contain the URL defined above for us to test.
3. You can use any programming language to build the application, as long it’s supported by IBM Cloud, has an api, provides a UI, and meets the spec criteria.
4. Detailed instructions on deploying and testing it locally, You should also submit your conversation workspace.

Review Guidelines

1. Richness of Model

• Does the model utilize and exploit NLU and Personality Insights features?
• Richness of model will not score any points  if there is no implementation. However, the implementation could be for a section of the model.  

2. Implementation

• IBM Discovery/NLU/Personality Insights features used to demonstrate the solution
• Design and code quality

3. Documentation

• A document explaining your solution.  How are you enhancing the output?
• A demo video of your solution

4. Ease of Use

• How easy it is to set up and test the solution
• User Interface - Functional interface should be sufficient to get a pass score.