Views
No views yet
neulab/reatt-large-nq-fid (based on T5 architecture) is initialized with neulab/reatt-large-nq and adapted on FiQA dataset with end-to-end retrieval-augmented training.1@inproceedings{jiang-etal-2022-reatt,
2 title = {Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer},
3 author = {Zhengbao Jiang and Luyu Gao and Jun Araki and Haibo Ding and Zhiruo Wang and Jamie Callan and Graham Neubig},
4 booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)},
5 address = {Abu Dhabi, UAE},
6 month = {December},
7 year = {2022}
8}