natural language processing

During the master we are given a choice of projects to work on within one semester. This was one of them in a team of 6 students. The following text is taken from our GitHub repository: This Master Research Project dealt with the creation and evaluation of a natural language processing tool to improve the scientific style of sentences without changing their semantic content. In a first step we have fine-tuned GPT-2 and T5 pretrained models using a previously proven pseudo-parallel dataset of original and paraphrased sentences to generate pseudo parallel data by paraphrasing a heavily filtered set of scientific sentences....

Description In a group of two, we worked on a project for the master’s course “Information Retrieval and Text Mining”. This project retrieves information from the Sherlock Holmes stories by using a number of text mining techniques and validates their correctness with quality measures based on a kappa distance verified dataset after adding annotations with tagtog. This text mining project concerned the analysis of all 60 Sherlock Holmes narratives. During the project, we preprocessed the stories, created a validation set for the Stanford coreNLP NER annotator by using tagtog on 100 data samples with 4 independent judges....