Ph.D. Studies

Overview

I am working on a dissertation in the field of natural language processing (NLP). The dissertation is part of a computer science Ph.D. program at the University of St. Gallen.

The tool, which is developed as part of the dissertation, will be a retrieval-augmented generator for financial documents. This means that one can provide a question and a PDF (with an annual report, for example) and get the answer to the question based on the PDF.

Modules in the finrag-sequence project:

|-pdf
|-embeddings
|-document_retriever
|-generator

This is the chair’s website.

Dissertation Progress

Course #1:          |##########| 100%
Course #2:          |##########| 100%
Course #3:          |##########| 100%
Proposal:           |##########| 100% Done and passed.
Research software:  |##--------| 20% (MVP is ready) -> Decided not to write a big overarching software project; each individual paper is based on its own code.
Paper #1:           |########--| 80% Needs to be published.
Paper #2:           |########--| 80% Needs to be published.
Paper #3:           |##--------| 20% Being written...
Paper #4:           |##--------| 20% Being written...
Defense:            |----------|  0%

Ph.D. Studies

Overview

Dissertation Progress

Read More From the 75 Steps Toward a Ph.D. in NLP Series