CO-NNECT

This repository contains our path generation framework Co-NNECT, in which we combine two models for establishing knowledge relations and paths between concepts from sentences, as a form of explicitation of implicit knowledge: COREC-LM (COmmonsense knowledge RElation Classification using Language Models), a relation classification system that we developed for classifying commonsense knowledge relations (CO-NNECT/COREC-LM); and COMET, a target prediction system developed by Bosselut et al., 2019, which we adapt for Forwardchaining (CO-NNECT/Forwardchaining).

本代码仓库收录了我们提出的路径生成框架Co-NNECT。该框架结合了两类模型，用于从语句中抽取概念间的知识关系与路径，以实现隐性知识的显式化：其一为我们自研的常识知识关系分类语言模型（COREC-LM，COmmonsense knowledge RElation Classification using Language Models），即Co-NNECT/COREC-LM模块，用于对常识知识关系进行分类；其二为Bosselut等人2019年提出的目标预测系统COMET，我们将其适配用于前向链式推理（Forwardchaining），即Co-NNECT/前向链式推理模块。