QA generation on sub sentences - NLP

Question

My dataset is structured like this:

Product1 - Sentence1

Product2 - Sentence2

Product3 - Sentence3

. .

etc

The sentences look like this:

Product1 - "We suggest that you wear this stylish piece with gold-toned drop earrings, churidar leggings and flats to complete an understated look."

A possible question to this can be - "Do we suggest that you wear this stylish piece with gold-toned drop earrings, churidar leggings and flats to complete an understated look?" - This is what i get using http://www.cs.cmu.edu/~ark/mheilman/questions/

But, I want questions/answers like this:

Q: How can I get an understated look?

A: You can try Product1 for an understated look.

Q: What can I wear with gold-toned drop earrings?

A: You can wear Product1 with gold-toned drop earrings.

Q: What will give me a complete look with churidar leggings?

A: Product1 will.

So, what i feel I want to do is - to create sub-question on the nouns/proNouns and adjectives in an semantically correct putting product in context.

Jealous

what exactly is your question? – Cordillera

Hey, @MattiLyra, which part you want me to explain further ? – Jealous

all of it, you haven't asked a question, you've outlined ways of solving a problem you have, but it is unclear what you expect the community to do for you, solve the problem for you, suggest APIs you could use or something else. Your question should be explicit and concise - please have a look at the help center for guidelines on good questions stackoverflow.com/help/on-topic – Cordillera

@MattiLyra - I have precisely mentioned the output I want from the dataset I have. Which basically means a complete solution is appreciated - In case that is not possible any guidance on API's etc is appreciated. – Jealous

Answer 1

Please have a look at Google Cloud Natural Language API

It has 'Entity Recognition' which might help your purpose. Here are the some sample implementations.

Collateral

Let me try this if I can extract (relevant phrases - noun phrases) using these API's. Will keep this thread updated. – Jealous

Answer 2

I suggest you to take a look for natural language services on the internet. Sometimes ago I had a similar problem and I solved it by using a service that you can finde here.

On the website this is defined as:

"API.AI is a natural language understanding platform that makes it easy for developers (and non-developers) to design and integrate intelligent and sophisticated conversational user interfaces into mobile apps, web applications, devices, and bots."

The really cool thing about this is that you can train it with some

Mer

Yes, I know about this and have used it also. This is focussed more towards creating heuristic rules to identify the context with a word match. This is not generic to any context and hence can't be used in my case. Appreciate the help! – Jealous