Gallery — Recent

This project focuses on a modification of a greedy transition based dependency parser. Typically a Part-Of-Speech (POS) tagger models a probability distribution over all the possible tags for each word in the given sentence and chooses one as its best guess. This is then pass on to the parser which uses this information to build a parse tree. The current state of the art for POS tagging is about 97% word accuracy, which seems high but results in a around 56% sentence accuracy. Small errors at the POS tagging phase can lead to large errors down the NLP pipeline and transition based parsers are particularity sensitive to these types of mistakes. A maximum entropy Markov model was trained as a POS multi-tagger passing more than its 1-best guess to the parser which was thought could make a better decision when committing to a parse for the sentence. This has been shown to give improved accuracy in other parsing approaches. We shown there is a correlation between tagging ambiguity and parsers accuracy and in fact the higher the average tags per word the higher the accuracy.

An "as simple as it gets" article template with a cover page, a dedicated content file and a main file.

This template outlines the different sections that are required for the reports for the lab course in TNM079 at Linköping University. The content has been updated for the course year 2020. Students are encouraged to use the source of this template to produce own lab reports. Each section title is followed by a short description and possible requirements.

This template is for authors who are preparing a manuscript for a Taylor & Francis journal using the \(\mathrm{\LaTeX}\) document preparation system and the interact class file, which is available via selected journals' home pages on the Taylor & Francis website.

You can use this template for your BTP Report at Netaji Subhas University of Technology (formerly, Netaji Subhas Insitute of Technology) Delhi

Presentation with thin fonts, white background, grey blocks.

Akapo Yusuf Oviyon's Curriculum Vitae

D'après la charte graphique 2019 de l'ECL : https://campus.ec-lyon.fr/charte-logos-outils-4788.kjsp?RF=1460981314923

For citations, I would recommend natbib for its flexibility, particularly when named citation styles are used, but it also has useful features for plain and those of that ilk.