# Verb Physics: Relative Physical Knowledge of Actions and Objects

## TL;DR

This paper introduces a method to infer relative physical knowledge about actions and objects from natural language text by jointly learning object pair attributes and action implications, overcoming reporting bias.

## Contribution

It presents a novel joint inference approach to extract relative physical knowledge from text, addressing the challenge of implicit commonsense information.

## Key findings

- Knowledge extraction from language is feasible.
- Joint inference improves accuracy.
- Method captures implicit physical relationships.

## Abstract

Learning commonsense knowledge from natural language text is nontrivial due to reporting bias: people rarely state the obvious, e.g., "My house is bigger than me." However, while rarely stated explicitly, this trivial everyday knowledge does influence the way people talk about the world, which provides indirect clues to reason about the world. For example, a statement like, "Tyler entered his house" implies that his house is bigger than Tyler. In this paper, we present an approach to infer relative physical knowledge of actions and objects along five dimensions (e.g., size, weight, and strength) from unstructured natural language text. We frame knowledge acquisition as joint inference over two closely related problems: learning (1) relative physical knowledge of object pairs and (2) physical implications of actions when applied to those object pairs. Empirical results demonstrate that it is possible to extract knowledge of actions and objects from language and that joint inference over different types of knowledge improves performance.