paper-with-me

Papers

Things not Written in Text: Exploring Spatial Commonsense from Visual Signals

2022-03-15 · ACL 2022 5 · Xiao Liu, Da Yin, Yansong Feng, Dongyan Zhao

Spatial commonsense, the knowledge about spatial position and relationship between objects (like the relative size of a lion and a girl, and the position of a boy relative to a bicycle when cycling), is an important part of commonsense knowledge. Although pretrained language models (PLMs) succeed in many NLP tasks, they are shown to be ineffective in spatial commonsense reasoning. Starting from the observation that images are more likely to exhibit spatial commonsense than texts, we explore whether models with visual signals learn more spatial commonsense than text-based PLMs. We propose a spatial commonsense benchmark that focuses on the relative scales of objects, and the positional relationship between people and objects under different actions. We probe PLMs and models with visual signals, including vision-language pretrained models and image synthesis models, on this benchmark, and find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models. The spatial knowledge from image synthesis models also helps in natural language understanding tasks that require spatial commonsense.

📄 PDF Abstract BibTeX arXiv:2203.08075

Code (1)

xxxiaol/spatial-commonsense 공식 구현 pytorch

Tasks

Image GenerationNatural Language UnderstandingPosition

Similar Papers 제목 키워드 기반

Things not Written in Text: Exploring Spatial Commonsense from Visual Signals

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Spatial commonsense, the knowledge about spatial position and relationship between objects (like the relative size of a lion and a girl, and the position of a boy relative to a bicycle when cycling), is an important part…

Image GenerationNatural Language UnderstandingPosition

Learning Common Sense Through Visual Abstraction

2015-12-01 · ICCV 2015 12 · Ramakrishna Vedantam, Xiao Lin, Tanmay Batra, C. Lawrence Zitnick 외

Common sense is essential for building intelligent machines. While some commonsense knowledge is explicitly stated in human-generated text and can be learnt by mining the web, much of it is unwritten. It is often unneces…

Common Sense Reasoning

Multiview Contextual Commonsense Inference: A New Dataset and Task

2022-10-06 · Siqi Shen, Deepanway Ghosal, Navonil Majumder, Henry Lim 외

Contextual commonsense inference is the task of generating various types of explanations around the events in a dyadic dialogue, including cause, motivation, emotional reaction, and others. Producing a coherent and non-t…

Multiview Contextual Commonsense Inference

SafeText: A Benchmark for Exploring Physical Safety in Language Models

2022-10-18 · Sharon Levy, Emily Allaway, Melanie Subbiah, Lydia Chilton 외

Understanding what constitutes safe text is an important issue in natural language processing and can often prevent the deployment of models deemed harmful and unsafe. One such type of safety that has been scarcely studi…

Text Generation

COMET-M: Reasoning about Multiple Events in Complex Sentences

2023-05-24 · Sahithya Ravi, Raymond Ng, Vered Shwartz

Understanding the speaker's intended meaning often involves drawing commonsense inferences to reason about what is not stated explicitly. In multi-event sentences, it requires understanding the relationships between even…

coreference-resolutionCoreference ResolutionSentence