Bias in Semantic and Discourse Interpretation
This work addresses interpretive bias, which is essential for learning and understanding but can be misused to distort truth, providing a foundational framework for researchers in linguistics and AI.
The paper tackles the problem of interpretive bias in semantic and discourse interpretation by developing a game-theoretic framework combined with discourse structure theory, resulting in tools for analyzing the range and contributing factors of such biases.
In this paper, we show how game-theoretic work on conversation combined with a theory of discourse structure provides a framework for studying interpretive bias. Interpretive bias is an essential feature of learning and understanding but also something that can be used to pervert or subvert the truth. The framework we develop here provides tools for understanding and analyzing the range of interpretive biases and the factors that contribute to them.