There are 7 repositories under commonsense-reasoning topic.
[ACL 2023] Reasoning with Language Model Prompting: A Survey
[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖
PaL: Program-Aided Language Models (ICML 2023)
[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
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)
Knowledge-Aware RL agents with Commonsense Reasoning
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.
[Paper][ISWC 2021] Zero-shot Visual Question Answering using Knowledge Graph
Automated Storytelling via Causal, Commonsense Plot Ordering
Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.
[CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. The code used in our paper "From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering", CVPR2022.
Codes for the WWW2021 paper: DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge (https://arxiv.org/abs/2101.00154).
Robot Commonsense Games
Official implementation of "Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models"
[Work in progress] A reading list for machine commonsense reasoning
This repository contains the PyTorch implementation of the paper STaCK: Sentence Ordering with Temporal Commonsense Knowledge appearing at EMNLP 2021.
This repository contains the dataset and the pytorch implementations of the models from the paper CIDER: Commonsense Inference for Dialogue Explanation and Reasoning. CIDER has been accepted to appear at SIGDIAL 2021.
Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.
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
📝 Source code for "ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation" (SemEval 2020).
The data and code for NumerSense (EMNLP2020)
Code for SCOPE (Style transfer through COmmonsense PropErty) , a style transfer approach to convert literal sentences to similes
The corresponding code from our paper " COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion (ACL 2021)". Do not hesitate to open an issue if you run into any trouble!
Knowledge-Augmented Language Models for Cause-Effect Relation Classification https://arxiv.org/abs/2112.08615
Uncertain Knowledge Graphs Embedding with BERT Pretrained Language Model
[EMNLP 2023] Knowledge Rumination for Pre-trained Language Models