[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖
-
Updated
Mar 12, 2023 - Python
[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖
Knowledge-Aware Graph Networks for Commonsense Reasoning (EMNLP-IJCNLP 19)
PaL: Program-Aided Language Models (ICML 2023)
[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
A set of utilities for running few-shot prompting experiments on large-language models
Experimental Python implementation of the Clarion cognitive architecture
[Paper][ISWC 2021] Zero-shot Visual Question Answering using Knowledge Graph
Language Models of Code are Few-Shot Commonsense Learners (EMNLP 2022)
Automated Storytelling via Causal, Commonsense Plot Ordering
The data and code for NumerSense (EMNLP2020)
This repository contains the PyTorch implementation of the paper STaCK: Sentence Ordering with Temporal Commonsense Knowledge appearing at EMNLP 2021.
Source code for the paper "Attention Is (not) All You Need for Commonsense Reasoning" published at ACL 2019.
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.
A Python Commonsense Knowledge Inference Toolkit
Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.
Data and code for the "Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences" (Emelin et al., 2021) paper.
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.
Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
Add a description, image, and links to the commonsense-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the commonsense-reasoning topic, visit your repo's landing page and select "manage topics."