Robust Retrieval Augmented Generation for Zero-shot Slot Filling

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


Abstract
Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI. One way to make headway for this problem is through advancements in a related task known as slot filling. In this task, given an entity query in form of [Entity, Slot, ?], a system is asked to ‘fill’ the slot by generating or extracting the missing value exploiting evidence extracted from relevant passage(s) in the given document collection. The recent works in the field try to solve this task in an end-to-end fashion using retrieval-based language models. In this paper, we present a novel approach to zero-shot slot filling that extends dense passage retrieval with hard negatives and robust training procedures for retrieval augmented generation models. Our model reports large improvements on both T-REx and zsRE slot filling datasets, improving both passage retrieval and slot value generation, and ranking at the top-1 position in the KILT leaderboard. Moreover, we demonstrate the robustness of our system showing its domain adaptation capability on a new variant of the TACRED dataset for slot filling, through a combination of zero/few-shot learning. We release the source code and pre-trained models.
Anthology ID:
2021.emnlp-main.148
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1939–1949
Language:
URL:
https://aclanthology.org/2021.emnlp-main.148
DOI:
10.18653/v1/2021.emnlp-main.148
Bibkey:
Cite (ACL):
Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, and Alfio Gliozzo. 2021. Robust Retrieval Augmented Generation for Zero-shot Slot Filling. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1939–1949, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Robust Retrieval Augmented Generation for Zero-shot Slot Filling (Glass et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.148.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.148.mp4
Code
 ibm/kgi-slot-filling +  additional community code
Data
KILTNatural QuestionsT-REx