In this article we employ whiteness as a conceptual framework to contextualize how faculty develop and implement, and consequently how students experience, service learning. A vignette that illustrates the pervasiveness of whiteness in service learning is followed by an analysis that details how whiteness frames the teaching and learning in this service learning experience. Through this example and analysis, we seek to increase instructors' capacity and confidence to interrupt the patterns and privileges of whiteness that too often are normalized in service learning.

In this paper, we present a method for adversarial decomposition of text representation. This method can be used to decompose a representation of an input sentence into several independent vectors, each of them responsible for a specific aspect of the input sentence. We evaluate the proposed method on two case studies: the conversion between different social registers and diachronic language change. We show that the proposed method is capable of fine-grained controlled change of these aspects of the input sentence. It is also learning a continuous (rather than categorical) representation of the style of the sentence, which is more linguistically realistic. The model uses adversarial-motivational training and includes a special motivational loss, which acts opposite to the discriminator and encourages a better decomposition. Furthermore, we evaluate the obtained meaning embeddings on a downstream task of paraphrase detection and show that they significantly outperform the embeddings of a regular autoencoder.

No abstract

No abstract

No abstract