ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

Abstract

We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as typed if-then relations with variables (e.g., "if X pays Y a compliment, then Y will likely return the compliment"). We propose nine if-then relation types to distinguish causes vs. effects, agents vs. themes, voluntary vs. involuntary events, and actions vs. mental states. By generatively training on the rich inferential knowledge described in ATOMIC, we show that neural models can acquire simple commonsense capabilities and reason about previously unseen events. Experimental results demonstrate that multitask models that incorporate the hierarchical structure of if-then relation types lead to more accurate inference compared to models trained in isolation, as measured by both automatic and human evaluation.

Understanding Commonsense Inference Aptitude of Deep Contextual Representations

“…We query a suite of knowledge bases (Concept-Net (Speer and Havasi, 2013), WebChild (Tandon et al, 2017), ATOMIC (Sap et al, 2019)) to create knowledge graph embeddings. First, we examine all relationships, indexing each unique relationship sequentially.…”

COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

“…to model "entities" as natural language phrases and relations as any concept that can link them (Li et al, 2016;Sap et al, 2019). OpenIE approaches display this property of open text entities and relations Mausam et al, 2012), but being extractive, they only capture knowledge that is explicitly mentioned in text, limiting their applicability for capturing commonsense knowledge, which is often implicit (Gordon and Van Durme, 2013).…”

Event Representation Learning Enhanced with External Commonsense Knowledge

“…One challenge for incorporating intents into event embeddings is that we should have a largescale labeled dataset, which annotated the event and its actor's intents. Recently, Rashkin et al (2018) and Sap et al (2019) released such valuable commonsense knowledge dataset (ATOMIC), which consists of 25,000 event phrases covering a diverse range of daily-life events and situations. For example, given an event "PersonX drinks coffee in the morning", the dataset labels PersonX's likely intent is "PersonX wants to stay awake".…”

“…Hence, intent and sentiment can be used to learn more fine-grained semantic features for event embeddings. Such commonsense knowledge is not explicitly expressed but can be found in a knowledge base such as Event2Mind (Rashkin et al, 2018) and ATOMIC (Sap et al, 2019). Thus, we aim to incorporate the external commonsense knowledge, i.e., intent and sentiment, into the learning process to generate better event representations.…”