Modeling Cross-Cultural Pragmatic Inference with Codenames Duet
This work addresses the challenge of incorporating sociocultural factors into pragmatic reasoning models for natural language processing, though it is incremental as it builds on existing reference game frameworks.
The authors tackled the problem of modeling how sociocultural background influences pragmatic inference in communication by introducing the Cultural Codes dataset based on Codenames Duet, showing that accounting for background characteristics significantly improves model performance for clue giving and guessing tasks.
Pragmatic reference enables efficient interpersonal communication. Prior work uses simple reference games to test models of pragmatic reasoning, often with unidentified speakers and listeners. In practice, however, speakers' sociocultural background shapes their pragmatic assumptions. For example, readers of this paper assume NLP refers to "Natural Language Processing," and not "Neuro-linguistic Programming." This work introduces the Cultural Codes dataset, which operationalizes sociocultural pragmatic inference in a simple word reference game. Cultural Codes is based on the multi-turn collaborative two-player game, Codenames Duet. Our dataset consists of 794 games with 7,703 turns, distributed across 153 unique players. Alongside gameplay, we collect information about players' personalities, values, and demographics. Utilizing theories of communication and pragmatics, we predict each player's actions via joint modeling of their sociocultural priors and the game context. Our experiments show that accounting for background characteristics significantly improves model performance for tasks related to both clue giving and guessing, indicating that sociocultural priors play a vital role in gameplay decisions.