PIQA: Reasoning about Physical Commonsense in Natural Language
Explore this paper's citation graph
Summary
The task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA are introduced and analysis about the dimensions of knowledge that existing models lack are provided, which offers significant opportunities for future research.
- Type
- preprint
- Published
- 2019-11-26
- Cited by
- 3,426
- References
- 41
- Access
- Open access
- OpenAlex
- https://openalex.org/W2989588035
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:208290939
Keywords
Commonsense reasoning, Commonsense knowledge, Question answering, Computer science, Encyclopedia
References
- Concreteness ratings for 40 thousand generally known English word lemmas
- Conceptual precursors to language
- Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Moving beyond the Turing Test with the Allen AI Science Challenge
- Situation Recognition: Visual Semantic Role Labeling for Image Understanding
- Physical Causality of Action Verbs in Grounded Language Understanding
- Learning Multi-Modal Grounded Linguistic Semantics by Playing "I Spy"
- SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
- Learning to See Physics via Visual De-animation
- Annotation Artifacts in Natural Language Inference Data
- Quantifying the Visual Concreteness of Words and Topics in Multimodal Datasets
- Hypothesis Only Baselines in Natural Language Inference
- Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
- Grounded Language Learning: Where Robotics and NLP Meet
- SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
- From Recognition to Cognition: Visual Commonsense Reasoning
- Assessing BERT's Syntactic Abilities
- HAKE: Human Activity Knowledge Engine
- Benchmarking Hierarchical Script Knowledge
Cited by
- Natural Adversarial Examples
- Natural Language QA Approaches using Reasoning with External Knowledge
- Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning
- Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
- Evaluating Machines by their Real-World Language Use
- How Additional Knowledge can Improve Natural Language Commonsense Question Answering
- Unsupervised Commonsense Question Answering with Self-Talk
- Experience Grounds Language
- UnifiedQA: Crossing Format Boundaries With a Single QA System
- Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models
- Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge
- ESPRIT: Explaining Solutions to Physical Reasoning Tasks
- How Context Affects Language Models' Factual Predictions
- XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
- ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning
- Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks
- Consolidating Commonsense Knowledge
- ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis
- Aligning AI With Shared Human Values
Related papers
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Abductive Commonsense Reasoning
- Social IQa: Commonsense Reasoning about Social Interactions
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- How Additional Knowledge can Improve Natural Language Commonsense Question Answering
- WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge
- CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge