Machine learning models are now able to convert user-written text descriptions into naturalistic images. These models are available to anyone online and are being used to generate millions of images a day. We investigate these models and find that …
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms …
The social impact of natural language processing and its applications has received increasing attention. In this position paper, we focus on the problem of safety for end-to-end conversational AI. We survey the problem landscape therein, introducing …
Recently, there has been an increased interest in demographically grounded bias in natural language processing (NLP) applications. Much of the recent work has focused on describing bias and providing an overview of bias in a larger context. Here, we …
An increasing number of natural language processing papers address the effect of bias on predictions, introducing mitigation techniques at different parts of the standard NLP pipeline (data and models). However, these works have been conducted …
The main goal of machine translation has been to convey the correct content. Stylistic considerations have been at best secondary. We show that as a consequence, the output of three commercial machine translation systems (Bing, DeepL, Google) make …
Several linguistic studies have shown the prevalence of various lexical and grammatical patterns in texts authored by a person of a particular gender, but models for part-of-speech tagging and dependency parsing have still not adapted to account for …