Gender Stereotypes

As robots enter more and more areas of everyday life, it becomes necessary for them to interact in an understandable and trustworthy way. In many regards this requires a human-like …...

AbstractWhen translating “The secretary asked for details.” to a language with grammatical gender, it might be necessary to determine the gender of the subject “secretary”. If the sentence does not …...

AbstractWhile language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a general framework to probe and …...

AbstractPrevious research has found that task-oriented conversational agents are perceived more positively by users when they provide information in an empathetic manner compared to a plain, emotionless information exchange. However, …...

AbstractWord embeddings learn implicit biases from linguistic regularities captured by word co-occurrence statistics. By extending methods that quantify human-like biases in word embeddings, we introduce ValNorm, a novel intrinsic evaluation …...