Robust Retrieval Augmented Generation for Zero-shot Slot Filling

TL;DR

This paper introduces a robust retrieval augmented generation approach with enhanced dense passage retrieval and training techniques for zero-shot slot filling, significantly improving performance and domain adaptability.

Contribution

It presents a novel retrieval augmented generation method with hard negatives and robust training for zero-shot slot filling, outperforming existing models.

Findings

Achieved top-1 ranking on KILT leaderboard.

Significant improvements on T-REx and zsRE datasets.

Demonstrated domain adaptation on TACRED dataset.

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.