GitHub topics: knowledge-paths
Heidelberg-NLP/LMs4Implicit-Knowledge-Generation Fork of maria-becker/LMs4Implicit-Knowledge-Generation
Code for equipping pretrained language models (BART, GPT-2, XLNet) with commonsense knowledge for generating implicit knowledge statements between two sentences, by (i) finetuning the models on corpora enriched with implicit information; and by (ii) constraining models with key concepts and commonsense knowledge paths connecting them.
Language: Python - Size: 128 KB - Last synced at: almost 2 years ago - Pushed at: almost 4 years ago - Stars: 14 - Forks: 3
Heidelberg-NLP/CO-NNECT Fork of maria-becker/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; and COMET, a target prediction system developed by Bosselut et al., 2019.
Language: Python - Size: 2.32 MB - Last synced at: almost 2 years ago - Pushed at: about 4 years ago - Stars: 9 - Forks: 1
maria-becker/LMs4Implicit-Knowledge-Generation
Code for equipping pretrained language models (BART, GPT-2, XLNet) with commonsense knowledge for generating implicit knowledge statements between two sentences, by (i) finetuning the models on corpora enriched with implicit information; and by (ii) constraining models with key concepts and commonsense knowledge paths connecting them.
Language: Python - Size: 128 KB - Last synced at: almost 2 years ago - Pushed at: almost 4 years ago - Stars: 6 - Forks: 4
maria-becker/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; and COMET, a target prediction system developed by Bosselut et al., 2019.
Language: Python - Size: 2.31 MB - Last synced at: almost 2 years ago - Pushed at: about 4 years ago - Stars: 1 - Forks: 3