📖 Use Bi-normal Separation to find document vectors which is used to compute similarity for shorter sentences.

Short Text Similarity as described in https://dl.acm.org/citation.cfm?id=2806475

There are existing methods in Natural Language Processing (NLP) which can find similarity between two longer texts (based on word co-occurence and statistics) but this project deals with shorter texts. It undertakes semantics and syntatic strucutre of a sentence.

A tool for semantic textual similarity annotation

A collection of Semantic Textual Similarity (STS) models and a framework for their evaluation on STS corpora with fine-grained similarity scores

An ad-blocker that secretly censors content at the deployer's disposal. HPI based project aiming to raise awareness about possible adverse effects of AI.