Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces
This addresses a challenge in semantic theory for NLP applications, offering a method to enhance fairness in information retrieval, though it is incremental in applying existing disentanglement techniques to a new linguistic problem.
The paper tackles the problem of pretrained NLP models entangling denotation and connotation in word representations, proposing an adversarial neural network to disentangle them, which improves viewpoint diversity in document rankings by 15%.
In politics, neologisms are frequently invented for partisan objectives. For example, "undocumented workers" and "illegal aliens" refer to the same group of people (i.e., they have the same denotation), but they carry clearly different connotations. Examples like these have traditionally posed a challenge to reference-based semantic theories and led to increasing acceptance of alternative theories (e.g., Two-Factor Semantics) among philosophers and cognitive scientists. In NLP, however, popular pretrained models encode both denotation and connotation as one entangled representation. In this study, we propose an adversarial neural network that decomposes a pretrained representation as independent denotation and connotation representations. For intrinsic interpretability, we show that words with the same denotation but different connotations (e.g., "immigrants" vs. "aliens", "estate tax" vs. "death tax") move closer to each other in denotation space while moving further apart in connotation space. For extrinsic application, we train an information retrieval system with our disentangled representations and show that the denotation vectors improve the viewpoint diversity of document rankings.