KICE: A Knowledge Consolidation and Expansion Framework for Relation Extraction

Abstract

Machine Learning is often challenged by insufficient labeled data. Previous methods employing implicit commonsense knowledge of pre-trained language models (PLMs) or pattern-based symbolic knowledge have achieved great success in mitigating manual annotation efforts. In this paper, we focus on the collaboration among different knowledge sources and present KICE, a Knowledge-evolving framework by Iterative Consolidation and Expansion with the guidance of PLMs and rule-based patterns. Specifically, starting with limited labeled data as seeds, KICE first builds a Rule Generator by prompt-tuning to stimulate the rich knowledge distributed in PLMs, generate seed rules, and initialize the rules set. Afterwards, based on the rule-labeled data, the task model is trained in a self-training pipeline where the knowledge in rules set is consolidated with self-learned high-confidence rules. Finally, for the low-confidence rules, KICE solicits human-enlightened understanding and expands the knowledge coverage for better task model training. Our framework is verified on relation extraction (RE) task, and the experiments on TACRED show that the model performance (F1) grows from 33.24% to 79.84% with the enrichment of knowledge, outperforming all the baselines including other knowledgeable methods.

Reasoning Makes Good Annotators : An Automatic Task-specific Rules Distilling Framework for Low-resource Relation Extraction

“…Since self-training methods (Rosenberg et al, 2005) accumulate noise in pseudo labels (Hu et al, 2021b), some methods (Han et al, 2018;Lin et al, 2019) Ye and Ling, 2019). Recently, language models has shown their ability on various tasks based on prompting (Li et al, 2022a(Li et al, ,b, 2021Lu et al, 2023). Since the scale of KB is limited, PRBOOST (Zhang et al, 2022) asks PLM by prompt to predict the relation directly and take the predictions as rules.…”