Generate question with different types from any kind of text data and get answers for it.

Generate coherent and understandable text in Chinese

ConceptNet 🚀🚀 is a powerful semantic network that represents general knowledge in a machine-readable format.

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 …

An SVM based approach to solve the Winograd Schema Challenge

Public datasets for graph embedding

Julia API for ConceptNetNumberbatch

ConceptNet datasource for the linked data fragments server (Server.js)

Refined and expanded version of Chinese ConceptNet

/ru/ConceptNet5.7 Python wrapper

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 …

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.

a large-scale graph database created as a combination of multiple taxonomy backbones extracted from 5 existing knowledge graphs, namely: ConceptNet, DBpedia, WebIsAGraph, WordNet and the Wikipedia category hierarchy

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.

Code for building ConceptNet from raw data.

Code for generating Quasimodo, a commonsense knowledge base.

CauseNet: Towards a Causality Graph Extracted from the Web

📝 Source code for "ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation" (SemEval 2020).