-
Currently, the `eval` command allows to evaluate the predictive performance of a backend for a single training and test split. Unfortunately, splitting multi-class multi-label data into training and t…
-
Hi,
Maybe a framework like VueJS could be used instead of HTML + JS (JQuery + Bootstrap). I think the use case so far is perfect for a small app as Annif is right now.
But for #24 and onward, I …
-
It would be great to have a REST method were you could upload a compressed archive and then a model is trained. You probably would have to add the project configuration to the call. An alternative cou…
-
PR #663 is going to bring support for batch suggest operations.
The STWFSA backend could benefit from implementing _suggest_batch instead of _suggest. It could process a batch of texts with paralle…
-
I've a question about the usage of vacabularies in an ensemble. Given a vocabulary V which is used in an ensemble and two vocabularies V1 and V2, which are used by different backends of the ensemble (…
-
Create a list of models that we could potentially use to extract text from documents and suggest metadata. We will start with basic metadata like title, description, etc. and eventually move on to op…
-
## Description of the enhancement
Skosmos should display a nice API documentation such as https://api.finto.fi/doc/ by default at `/rest/v1/`. This can hopefully be generated from existing Swagger …
-
TUPrints needs to know DDC classification of the publication. This is likely not to be automated and hardly any metadata to find, so add a field to the form.
It should be considered to add a genera…
-
In Automated subject indexing (and multi label classification in general) the distribution of assigned concepts often follows Zipf's law. In our experience this leads to algorithms having low precisio…
-
We are currently using Gensim only for the basic TF-IDF backend. It should be almost trivial to create an LSI backend, it's just one extra LsiModel layer and a single parameter (number of dimensions).…