Commit
·
2311b4e
1
Parent(s):
4399bc6
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Fusion-in-Decoder (FiD) is a model described in the following paper:
|
| 2 |
+
|
| 3 |
+
> Izacard, Gautier, and Édouard Grave. [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://aclanthology.org/2021.eacl-main.74/). _Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume_. 2021.
|
| 4 |
+
|
| 5 |
+
We have replicated FiD training with our Wikipedia corpus variants and incorporated the model into our [PyGaggle](https://github.com/castorini/pygaggle) neural text ranking library.
|
| 6 |
+
|
| 7 |
+
Our own efforts are described in the paper entitled:
|
| 8 |
+
> Pre-Processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering.
|
| 9 |
+
|
| 10 |
+
This is a FiD-large reader model for the wiki-text-6-3 corpus variant trained on the TriviaQA dataset.
|