Finally, we conclude with some recommendations for how to created and document web-scale datasets from a scrape of the internet.
By treating a classification model's predictions for a given image as a set of labels analogous to a bag of words, we rank the biases that a model has learned with respect to different identity labels.
This white paper summarizes the authors' structured brainstorming regarding ethical considerations for creating an extensive repository of online content labeled with tags that describe potentially questionable content for young viewers.
In this paper, we introduce a rigorous framework for dataset development transparency which supports decision-making and accountability.
The ethical concept of fairness has recently been applied in machine learning (ML) settings to describe a wide range of constraints and objectives.
Although essential to revealing biased performance, well intentioned attempts at algorithmic auditing can have effects that may harm the very populations these measures are meant to protect.
Computers and Society
Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations deploying the algorithms.
Computers and Society
Data-driven statistical Natural Language Processing (NLP) techniques leverage large amounts of language data to build models that can understand language.
Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking.
We trace how the notion of fairness has been defined within the testing communities of education and hiring over the past half century, exploring the cultural and social context in which different fairness definitions have emerged.
Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information.
We introduce initial groundwork for estimating suicide risk and mental health in a deep learning framework.
We demonstrate an approach to face attribute detection that retains or improves attribute detection accuracy across gender and race subgroups by learning demographic information prior to learning the attribute detection task.
We present a method to improve video description generation by modeling higher-order interactions between video frames and described concepts.
As machines have become more intelligent, there has been a renewed interest in methods for measuring their intelligence.
1 code implementation • • Ting-Hao, Huang, Francis Ferraro, Nasrin Mostafazadeh, Ishan Misra, Aishwarya Agrawal, Jacob Devlin, Ross Girshick, Xiaodong He, Pushmeet Kohli, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh, Lucy Vanderwende, Michel Galley, Margaret Mitchell
We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling.
There has been an explosion of work in the vision & language community during the past few years from image captioning to video transcription, and answering questions about images.
When human annotators are given a choice about what to label in an image, they apply their own subjective judgments on what to ignore and what to mention.
Integrating vision and language has long been a dream in work on artificial intelligence (AI).
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs.
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations.
Two recent approaches have achieved state-of-the-art results in image captioning.
Given an image and a natural language question about the image, the task is to provide an accurate natural language answer.
no code implementations • • Hao Fang, Saurabh Gupta, Forrest Iandola, Rupesh Srivastava, Li Deng, Piotr Dollár, Jianfeng Gao, Xiaodong He, Margaret Mitchell, John C. Platt, C. Lawrence Zitnick, Geoffrey Zweig
The language model learns from a set of over 400, 000 image descriptions to capture the statistics of word usage.