KGI: An Integrated Framework for Knowledge Intensive Language Tasks

Md Faisal Mahbub Chowdhury, Michael Glass, Gaetano Rossiello, Alfio Gliozzo, Nandana Mihindukulasooriya


Abstract
In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering, dialogue, and fact-checking. Moreover, given a user query, we show how the output from these different models can be combined to cross-examine the outputs of each other. Particularly, we show how accuracy in dialogue can be improved using the question answering model. We are also releasing all models used in the demo as a contribution of this paper. A short video demonstrating the system is available at https://ibm.box.com/v/emnlp2022-demos.
Anthology ID:
2022.emnlp-demos.28
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
December
Year:
2022
Address:
Abu Dhabi, UAE
Editors:
Wanxiang Che, Ekaterina Shutova
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
282–288
Language:
URL:
https://aclanthology.org/2022.emnlp-demos.28
DOI:
10.18653/v1/2022.emnlp-demos.28
Bibkey:
Cite (ACL):
Md Faisal Mahbub Chowdhury, Michael Glass, Gaetano Rossiello, Alfio Gliozzo, and Nandana Mihindukulasooriya. 2022. KGI: An Integrated Framework for Knowledge Intensive Language Tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 282–288, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
KGI: An Integrated Framework for Knowledge Intensive Language Tasks (Chowdhury et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-demos.28.pdf