@tdouzon We don't have more training data for machine learning, unfortunately. You might try the following. In absence of training data, Mostafa Deghani and colleagues used "weak supervision" with BM25 as "signal", see: Mostafa Dehghani et al. "Neural Ranking Models with Weak Supervision", In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'17), 2017, pp 65-74.
@hiemstra thanks I'll give it a look !
I quite liked the blog post too:
Good luck w/ your project!
A social network for the University of Twente community. Anyone with an @utwente.nl or @*.utwente.nl email address can create an account here and participate in the global fediverse with millions of other users. This means that students, staff and alumni can create an account here. Content does not reflect the opinions or policies of the University of Twente.
We support \( \LaTeX \) formulas: Use
\) for inline LaTeX formulas, and
\] for display mode.