Communications of the ACM
The Missing Voices in Natural Language Processing
Much of the current state-of-the-art performance in NLP requires large datasets, which has pushed concerns about the perspectives represented in the data to the side.
Credit: Getty Images
Recent advancements in natural language processing (NLP) have been truly astonishing. From translation to voice assistants and the synthesis of research on viruses like COVID-19, NLP has radically altered the technology we use.
But further advancements will not only require the work of the entire NLP community, but also that of cross-functional groups and disciplines. Rather than pursuing marginal gains on metrics, we should target true "transformative" change, which means understanding who is being left behind and including their values in the conversation.
From The Gradient
View Full Article
No entries found