AI program for creating a paragraph template

Question

Is there any software or service or AI program that can rebuild an English paragraph using a different set of vocabulary, grammar rules, etc.

I want to say if the original paragraph

"Gwalior is a good tourist spot close to Jhansi. Jhansi is very famous for their queen Rani Lakshmi Bai (Manikandana)"

Any software can generate its own version or template, for example

"Rani Lakshmi Bai (Manicandana) was Queen Jhansi, who is closer to the good tourist palace of Gwalior."

Or something else. I know that 100% correctness is impossible before human intervention.

Answer 1

Rapid Rewrite is software that can do what you need: http://www.rapidrewriter.com/?hop=qushy It's not free, although the site is terrible.

Here's another one - the same story http://thebestspinner.com/?id=eprocent

watch their videos and tell me that not what you are looking for ...

Answer 2

This guy wrote a JavaScript application that generates corporate crap ready for distribution (he also got a great bingo word generator ). This is not AI, it just follows linguistic rules. From what I understand about your question, you don't need AI, you could learn a lot by just learning what this guy did. He minifies the program with nouns, verbs, adjectives, adverbs, etc. And it generates text that your eyes can analyze (it's grammatical, but that doesn't necessarily make sense). If you are looking for something to write your dissertation, you are much more interested in doing it.

From your question, it looks like you are also looking for a program for parsing the English language and generating source data for the previously mentioned generator. Abiword uses such a grammar analyzer to verify grammar. I did not look at it to a large extent, but I suppose you could easily use it to list the parts of speech contained in a section of text. If you used this program to generate seed data, you could pump the output directly into another program to generate more text.

Answer 3

The Python NLTK library performs natural language analysis, including creating parsing trees that include whether a word is a verb, noun, tense, etc. Perhaps you could take these trees and re-arrange them according to some simple rules that you have come up with and verified. I do not think that you will need too many rules before the results of your program are very different from the original document. Some examples of rules:

• Replace words with synonyms
• active voice to a passive voice and vice versa (the hunter saw the deer → the deer was seen by the hunter)

http://www.nltk.org/

Answer 4

Here are some links to various programs for changing the written text. One of them should be able to provide you with some tips on how to implement what you are looking for.

• http://www.worldlingo.com/ma/enwiki/en/Jive_filter
• http://bytes.com/topic/python/answers/476939-filters-like-old-skool-jive-fudd-valspeak-text-transformation-python
• http://www.rinkworks.com/dialect/

Answer 5

I do not agree that NLP is not the way you need it.

However, if you do not want to follow the NLP route, you can generate good sound sentences without using NLP by training a custom language model using n-grams to create a fourth or fifth order model. Then you used statistical probability to generate offers.

As soon as you have your model, you arbitrarily choose the initial word (in the area of ​​known words beginning with words or words starting with an uppercase letter), and then conditionally presumably choose the next word.

An easy example of this in this article: Wordmills are coming ...

Of course, for this you will need sufficient training material, since just learning a simple paragraph will not work well for how you want to rephrase the paragraph. Without using NLP methods to define nouns, verbs, etc. From your sample (which will also require well-trained models) and then reordering them using the opposite sentence structure will be more effort than just using NLP.

What you are trying to do is extract the entity as well as the location information. Not only that, but also the relationship between entities and locations. Very high order if you are not going to use NLP.