Social Chemistry 101: Learning to Reason about Social and Moral Norms

Abstract

Social norms-the unspoken commonsense rules about acceptable social behavior-are crucial in understanding the underlying causes and intents of people's actions in narratives. For example, underlying an action such as "wanting to call cops on my neighbor" are social norms that inform our conduct, such as "It is expected that you report crimes." We present SOCIAL CHEMISTRY, a new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language. We introduce SOCIAL-CHEM-101, a large-scale corpus that catalogs 292k rules-of-thumb such as "It is rude to run a blender at 5am" as the basic conceptual units. Each rule-of-thumb is further broken down with 12 different dimensions of people's judgments, including social judgments of good and bad, moral foundations, expected cultural pressure, and assumed legality, which together amount to over 4.5 million annotations of categorical labels and free-text descriptions. Comprehensive empirical results based on state-of-the-art neural models demonstrate that computational modeling of social norms is a promising research direction. Our model framework, NEURAL NORM TRANSFORMER, learns and generalizes SOCIAL-CHEM-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb. 1 Note that the social identities of the participants of situations would further inform which social norms are most

Thinking Like a Skeptic: Defeasible Inference in Natural Language

“…guage. 1 δ-NLI is a collection of extensions to three existing English-language inference datasets, covering a broad range phenomena: natural language inference (SNLI (Bowman et al, 2015)), commonsense reasoning (ATOMIC (Sap et al, 2019)), and reasoning about social norms (SOCIAL-CHEM-101 (Forbes et al, 2020)). We refer to these subsections of the dataset as δ-SNLI, δ-ATOMIC, and δ-SOCIAL, respectively.…”

“…The SOCIAL-CHEM-101 dataset of social norms (henceforth, Social Norms) compiles a collection of 292K crowdsourced natural language statements about commonsense social judgments made given everyday situations (Forbes et al, 2020). These statements represent generic commonsense hypotheses about social behaviors and their acceptability that are held as norms in a society.…”

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset

“…Since the proposal of Cyc (Lenat, 1995) and Con-ceptNet (Liu and Singh, 2004;Speer et al, 2017), a growing number of large-scale human-annotated CSKBs are developed Bisk et al, 2020;Mostafazadeh et al, 2020;Forbes et al, 2020;Lourie et al, 2020;Ilievski et al, 2020). While ConceptNet mainly depicts the commonsense relations between entities and only small portion of events, recent important CSKBs have been more devoted to event-centric commonsense knowledge.…”

“…Another CSKB is GLUCOSE (Mostafazadeh et al, 2020), which extracts sentences from ROC Stories and defines 10 commonsense dimensions to explores the causes and effects given the base event. In this paper, we select ConceptNet, ATOMIC, ATOMIC 20 20 , and GLUCOSE to align them together because they are all event-centric and relatively more normalized compared to other CSKBs like SocialChem-istry101 (Forbes et al, 2020).…”

“…The nodes in GLUCOSE are also normalized and syntactically parsed manually, where human-related pronouns are written as "SomeoneA" or "SomeoneB", and object-related pronouns are written as "SomethingA". Other commonsense resources like SocialChemistry101 (Forbes et al, 2020) are not selected as they include over looselystructured events.…”