# Joint Reasoning for Multi-Faceted Commonsense Knowledge

arXiv: https://arxiv.org/abs/2001.04170 · HTML: https://mlsanity.com/paper/2001.04170/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2020.

## Built on by (most cited first, 12 of 12)

- [FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery](https://mlsanity.com/paper/2211.08316/) (2022)
- [Refined Commonsense Knowledge from Large-Scale Web Contents](https://mlsanity.com/paper/2112.04596/) (2021)
- [AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation](https://mlsanity.com/paper/2402.10646/) (2024)
- [Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph](https://mlsanity.com/paper/2209.15214/) (2022)
- [PaCo: Preconditions Attributed to Commonsense Knowledge](https://mlsanity.com/paper/2104.08712/) (2021)
- [UnCommonSense: Informative Negative Knowledge about Everyday Concepts](https://mlsanity.com/paper/2208.09292/) (2022)
- [Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce](https://mlsanity.com/paper/2205.10843/) (2022)
- [Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering](https://mlsanity.com/paper/2105.13662/) (2021)
- [Materialized Knowledge Bases from Commonsense Transformers](https://mlsanity.com/paper/2112.14815/) (2021)
- [Adversarial Transformer Language Models for Contextual Commonsense Inference](https://mlsanity.com/paper/2302.05406/) (2023)
- [Do Children Texts Hold The Key To Commonsense Knowledge?](https://mlsanity.com/paper/2210.04530/) (2022)
- [Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary](https://mlsanity.com/paper/2210.06376/) (2022)

## Abstract (arXiv)

Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept. Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid. This paper aims to overcome these limitations by introducing a multi-faceted model of CSK statements and methods for joint reasoning over sets of inter-related statements. Our model captures four different dimensions of CSK statements: plausibility, typicality, remarkability and salience, with scoring and ranking along each dimension. For example, hyenas drinking water is typical but not salient, whereas hyenas eating carcasses is salient. For reasoning and ranking, we develop a method with soft constraints, to couple the inference over concepts that are related in in a taxonomic hierarchy. The reasoning is cast into an integer linear programming (ILP), and we leverage the theory of reduction costs of a relaxed LP to compute informative rankings. This methodology is applied to several large CSK collections. Our evaluation shows that we can consolidate these inputs into much cleaner and more expressive knowledge. Results are available at https://dice.mpi-inf.mpg.de.