projects
projects copied to clipboard
explosion
🪐 End-to-end NLP workflows from prototype to production
## Goals Implement a working draft picking entity candidates based on - similarities in the embedding space between entity description and text - fuzzy lexical similarity between entity name and...
This adds a training config for the new coref component using OntoNotes / CoNLL 2012 data. The current config works, but is relatively brittle in relation to the OntoNotes setup....
## Goals Remove dependency installation from project config files. The changes to install requirements per project in the scheduled BuildKitten job can be found in https://github.com/explosion/buildkite-pipelines/pull/9. ## Description - Remove...
This is required when loading from disk with a trained transformer based model.
## Description The weekly build currently fails on BuildKite to the usage of Python 3.7 and the `sqlite3` version shipped with it due to its lack of support of the...
## Description Adds a step for the comparison of multiple evaluations, to simplify comparing e.g. multiple candidate generators. This includes - persisting evaluation results as `.csv` files for every execution...
This is a project that is meant to help with experimenting with the `spancat` and `ner` components. Currently it has: 1. ConLL (English, German, Spanish, Dutch) 2. WiniNeuRal (English, German,...
## Description Update config to use `spacy.EntityLinker.v2` and `spacy.HashEmbedCNN.v2`. Oddly enough, this new v2 config doesn't manage to get beyond 33% F-score for the EL, while the previous v1 version...
## Description Various changes to NEL benchmark in order to integrate `WikiKB` (and fix a few things along the way). **Note**: Do NOT merge at this point. This leverages experimental...
## Description ### Types of change ## Checklist - [ ] I confirm that I have the right to submit this contribution under the project's MIT license. - [ ]...
