There are 3 repositories under commonsense-knowledge topic.
ASER (Activities, States, Events, and their Relations): a large-scale weighted eventuality knowledge graph.
CSKG: The CommonSense Knowledge Graph
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.
Codes for the WWW2021 paper: DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge (https://arxiv.org/abs/2101.00154).
COMET-ATOMIC ja
Codes and Datasets for the ACL2023 Findings Paper: FolkScope: Intention Knowledge Graph Construction for Discovering E-commerce Commonsense
Advanced Semantics for Commonsense Knowledge Extraction (WWW 2021)
Codes for the EMNLP2021 paper: Benchmarking Commonsense Knowledge Base Population (https://aclanthology.org/2021.emnlp-main.705.pdf). An updated version CKBP v2 (https://arxiv.org/pdf/2304.10392.pdf)
Code and data for the paper Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
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.
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.
Refined Commonsense Knowledge from Large-Scale Web Contents (TKDE 2022)
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.
NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment
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.
Dataset of a collection of commonsense knowledge assertions relevant for the autonomous driving (AD) domain.
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.
The official repository for creating casual action effect (CAE) dataset for the IJCNLP-AACL 2023 paper: Implicit Affordance Acquisition via Causal Action–Effect Modeling in the Video Domain
The official repository for the IJCNLP-AACL 2023 paper: Implicit Affordance Acquisition via Causal Action–Effect Modeling in the Video Domain
Bachelor's Thesis: "Be Constructive, Helpful and Empathetic: Towards Situated Empathic Dialogue Generation Grounded in Social and Moral Commonsense Knowledge"
This repository explores enhancing dialogue summarization with commonsense knowledge through the SICK framework, evaluating models on dialogue datasets to assess commonsense's impact on summarization quality.
Dataset and codes from the paper "AcTED: Automatic Acquisition of Typical Event Duration for Semi-supervised Temporal Commonsense QA"
Dataset from the paper "Improving Event Duration Question Answering by Leveraging Existing Temporal Information Extraction Data"
Code for the paper "Learning Prototypical Functions for Physical Artifacts"
Supplementary material for the paper "Commonsense Knowledge in Cognitive Robotics: A Systematic Literature Review"