word embeddings

In this paper, we describe and present the results of meme detection system, specifically developed and submitted for our participation …

As part of the DANKMEMES competition (EVALITA 2020), I developed a model for multimodal detection of political memes. The proposed solution is a feed-forward neural network that leverages pretrained embeddings, both for text and image representation.

I designed and developed the ML component of a system to identify the structure (chapters, paragraphs…) from an insurance document in PDF format. The extracted text and structure are saved in XML format.

As part of a search engine for institutional documents, I designed and developed a fast pipeline for the interpretation and expansion of the user query. In the query, named entities, dates, domain terms and complex terms are detected.