Fusion-in-Decoder (FiD) is a model described in the following paper:
Izacard, Gautier, and Édouard Grave.
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
.
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
. 2021.
We have replicated FiD training with our Wikipedia corpus variants and incorporated the model into our
PyGaggle
neural text ranking library.
Our own efforts are described in the paper entitled:
Pre-Processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering.
This is a FiD-large reader model for the wiki-text-100w corpus variant trained on the TriviaQA dataset.