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 …
Text contains a wealth of information about about a wide variety of sociocultural constructs. Automated prediction methods can infer these quantities (sentiment analysis is probably the most well-known application). However, there is virtually no …
Many tasks in Natural Language Processing (NLP) and Computer Vision (CV) offer evidence that humans disagree, from objective tasks such as part-of-speech tagging to more subjective tasks such as classifying an image or deciding whether a proposition …
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 …
There are some issues with current research trends in NLP that can hamper the free development of scientific research. We identify five of particular concern: 1) the early adoption of methods without sufficient understanding or analysis; 2) the …
Topic models extract groups of words from documents, whose interpretation as a topic hopefully allows for a better understanding of the data. However, the resulting word groups are often not coherent, making them harder to interpret. Recently, neural …
In an election campaign, political parties pledge to implement various projects--should they be elected. But do they follow through? To track election pledges from parties' election manifestos, we need to distinguish between pledges and general …
Language models have revolutionized the field of NLP. However, language models capture and proliferate hurtful stereotypes, especially in text generation. Our results show that **4.3% of the time, language models complete a sentence with a hurtful …
Natural language processing (NLP) applications are now more powerful and ubiquitous than ever before. With rapidly developing (neural) models and ever-more available data, current NLP models have access to more information than any human speaker …