@inproceedings{glass-etal-2021-robust,
title = "Robust Retrieval Augmented Generation for Zero-shot Slot Filling",
author = "Glass, Michael and
Rossiello, Gaetano and
Chowdhury, Md Faisal Mahbub and
Gliozzo, Alfio",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.148",
doi = "10.18653/v1/2021.emnlp-main.148",
pages = "1939--1949",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="glass-etal-2021-robust">
<titleInfo>
<title>Robust Retrieval Augmented Generation for Zero-shot Slot Filling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Glass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaetano</namePart>
<namePart type="family">Rossiello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Faisal</namePart>
<namePart type="given">Mahbub</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfio</namePart>
<namePart type="family">Gliozzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">glass-etal-2021-robust</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.148</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.148</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1939</start>
<end>1949</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robust Retrieval Augmented Generation for Zero-shot Slot Filling
%A Glass, Michael
%A Rossiello, Gaetano
%A Chowdhury, Md Faisal Mahbub
%A Gliozzo, Alfio
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F glass-etal-2021-robust
%X 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.
%R 10.18653/v1/2021.emnlp-main.148
%U https://aclanthology.org/2021.emnlp-main.148
%U https://doi.org/10.18653/v1/2021.emnlp-main.148
%P 1939-1949
Markdown (Informal)
[Robust Retrieval Augmented Generation for Zero-shot Slot Filling](https://aclanthology.org/2021.emnlp-main.148) (Glass et al., EMNLP 2021)
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.