What is semantic similarity?

The task of measuring sentence similarity is defined as determining how similar the meanings of two sentences are.

Why is it important?

Today we have an abboundance of text data, but the utilizing this resource if tricky as Computing sentence similarity is not a trivial task, due to the variability of natural language expressions. If done correctly, this metric could be used to collect, compare and classify large corpus of raw data, which could be utilized efficiently.

Real World Examples:

1. Medical : when a new case comes to an practicionar, he/she can look for similar case in past and get the most clossely ressembeling case and make better decisions.
2. Law : When a new case comes, law firms look over there database for similar cases in past and then stratergise from those case studies. ( Currently used by some firms )

There above examples are a reality but are still kept as an internal tool by organizations, as it brings them a competetive edge.

We wish to present this technology in the hands of general consumer with this platform where individuals and organizations will be able to

1. Collect
2. Compare
3. Classify Text data, which will accelerate there processes.

Possible Clinet base:

1. Law Firms
2. Hospitals
3. Schools -> checking google form (text) answers automatically
4. Researchers -> collecting news/information from different sources and classifiy them
5. Others.

1. https://github.com/brmson/dataset-sts/blob/master/data/sts/semeval-sts/2014/00-readme.test.txt