Deriving Commonsense Inference Tasks from Interactive Fictions

For example, most benchmarks When playing an Interactive Fiction (IF) game, we focus on collocation, association or other relations explore and progress through a fantasy world by observing (e.g., ConceptNet (Speer et al., 2016) relations) between textual descriptions and sending text commands words or concepts (Levesque et al., 2012; to control the protagonist. While in pure Talmor et al., 2019; Mullenbach et al., 2019; Jiang texts, we relate the implicit knowledge of these fantasy et al., 2020). Other examples include temporal commonsense worlds with those in our physical world. For (Zhou et al., 2019), physical interactions example, we explore unvisited regions by planning between action and objects (Bisk et al., 2020), emotions over the mentioned locations (spatial relations); we and behaviors of people under the given situation eat apples to recover health and attach the enemies (Sap et al., 2019b), and cause-effects between with swords, but not vice versa (physical interaction events and states (Sap et al., 2019a; Bhagavatula relations); we retrospect the poor choice of et al., 2019; Huang et al., 2019). Second, the task breaking the lantern when we find the protagonist form makes them more likely commonsense validation, in a dangerous dark wood (cause and effects). Plentiful i.e., validation between a commonsense fact and diverse commonsense knowledge from and a text statement, but neglecting hops among our physical world is encoded in our game playing multiple facts.