DISCOS-commonsense

[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs ?

Knowledge-Aware Graph Networks for Commonsense Reasoning (EMNLP-IJCNLP 19)

[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning

CSKG: The CommonSense Knowledge Graph

A set of utilities for running few-shot prompting experiments on large-language models

Language Models of Code are Few-Shot Commonsense Learners (EMNLP 2022)

[Paper][ISWC 2021] Zero-shot Visual Question Answering using Knowledge Graph

The purpose of this repository is to introduce new dialogue-level commonsense inference datasets and tasks. We chose dialogues as the data source because dialogues are known to be complex and rich in commonsense.

CoCo-Ex extracts meaningful concepts from natural language texts and maps them to conjunct concept nodes in ConceptNet, utilizing the maximum of relational information stored in the ConceptNet knowledge graph.