paper-with-me

Papers

ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion

2022-12-06 · Pei Chen, Wenlin Yao, Hongming Zhang, Xiaoman Pan, Dian Yu, Dong Yu, Jianshu Chen

Knowledge base completion (KBC) aims to predict the missing links in knowledge graphs. Previous KBC tasks and approaches mainly focus on the setting where all test entities and relations have appeared in the training set. However, there has been limited research on the zero-shot KBC settings, where we need to deal with unseen entities and relations that emerge in a constantly growing knowledge base. In this work, we systematically examine different possible scenarios of zero-shot KBC and develop a comprehensive benchmark, ZeroKBC, that covers these scenarios with diverse types of knowledge sources. Our systematic analysis reveals several missing yet important zero-shot KBC settings. Experimental results show that canonical and state-of-the-art KBC systems cannot achieve satisfactory performance on this challenging benchmark. By analyzing the strength and weaknesses of these systems on solving ZeroKBC, we further present several important observations and promising future directions.

📄 PDF Abstract BibTeX arXiv:2212.03091

Code (1)

brickee/zerokbc 공식 구현

Tasks

Knowledge Base CompletionKnowledge Graphs

Methods 이 논문이 사용한 방법론

Test 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

Benchmarking Knowledge-driven Zero-shot Learning

2021-06-29 · Yuxia Geng, Jiaoyan Chen, Xiang Zhuang, Zhuo Chen 외

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, suc…

AttributeBenchmarkingimage-classificationImage Classification+3

ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories

2023-05-24 · Heming Xia, Qingxiu Dong, Lei LI, Jingjing Xu 외

Recently, Large Language Models (LLMs) have been serving as general-purpose interfaces, posing a significant demand for comprehensive visual knowledge. However, it remains unclear how well current LLMs and their visually…

Common Sense Reasoning

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

2023-11-15 · Zhaowei Wang, Haochen Shi, Weiqi Wang, Tianqing Fang 외

Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present AbsPyramid, a unified entailment graph of 221K textual …

Benchmarking

SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation

2021-08-27 · ICCV 2021 10 · Jiaxin Cheng, Soumyaroop Nandi, Prem Natarajan, Wael Abd-Almageed

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixe…

Knowledge DistillationSegmentationSemantic Segmentationzero-shot-classification+2

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models

2023-08-19 · Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao 외

Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored, and their performance on compl…

Multiple-choice