Towards Generalized Open Information Extraction

11/29/2022
by   Bowen Yu, et al.
0

Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts. However, the prevailing solutions evaluate OpenIE models on in-domain test sets aside from the training corpus, which certainly violates the initial task principle of domain-independence. In this paper, we propose to advance OpenIE towards a more realistic scenario: generalizing over unseen target domains with different data distributions from the source training domains, termed Generalized OpenIE. For this purpose, we first introduce GLOBE, a large-scale human-annotated multi-domain OpenIE benchmark, to examine the robustness of recent OpenIE models to domain shifts, and the relative performance degradation of up to 70 OpenIE. Then, we propose DragonIE, which explores a minimalist graph expression of textual fact: directed acyclic graph, to improve the OpenIE generalization. Extensive experiments demonstrate that DragonIE beats the previous methods in both in-domain and out-of-domain settings by as much as 6.0 absolutely, but there is still ample room for improvement.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/29/2022

Domain-Unified Prompt Representations for Source-Free Domain Generalization

Domain generalization (DG), aiming to make models work on unseen domains...
research
03/21/2022

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Domain generalization (DG) aims to learn a generalized model to an unsee...
research
08/20/2023

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

Deep Neural Networks have exhibited considerable success in various visu...
research
06/19/2022

Finding Diverse and Predictable Subgraphs for Graph Domain Generalization

This paper focuses on out-of-distribution generalization on graphs where...
research
04/04/2023

Randomized Adversarial Style Perturbations for Domain Generalization

We propose a novel domain generalization technique, referred to as Rando...
research
05/05/2022

Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation

Open-domain conversational systems are assumed to generate equally good ...
research
06/15/2023

Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts

This paper explores methods for extracting information from radiology re...

Please sign up or login with your details

Forgot password? Click here to reset