M
Margaret Mitchell
Researcher at Google
Publications - 109
Citations - 18187
Margaret Mitchell is an academic researcher from Google. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 42, co-authored 94 publications receiving 13094 citations. Previous affiliations of Margaret Mitchell include University of Aberdeen & Johns Hopkins University.
Papers
More filters
Posted Content
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
Alessandro Sordoni,Michel Galley,Michael Auli,Chris Brockett,Yangfeng Ji,Margaret Mitchell,Jian-Yun Nie,Jianfeng Gao,Bill Dolan +8 more
TL;DR: This paper used a neural network architecture to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances and showed consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.
Posted Content
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
Michel Galley,Chris Brockett,Alessandro Sordoni,Yangfeng Ji,Michael Auli,Chris Quirk,Margaret Mitchell,Jianfeng Gao,Bill Dolan +8 more
TL;DR: This article introduced Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs, and showed that deltaBLEU correlates reasonably with human judgments and outperforms sentence-level and IBM bLEU in terms of Spearman's rho and Kendall's tau.
Proceedings Article
InclusiveFaceNet: Improving Face Attribute Detection with Race and Gender Diversity
TL;DR: 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 is demonstrated.
Posted Content
Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
Inioluwa Deborah Raji,Timnit Gebru,Margaret Mitchell,Joy Buolamwini,Joonseok Lee,Emily Denton +5 more
TL;DR: In this paper, the authors demonstrate a set of five ethical concerns in the particular case of auditing commercial facial processing technology, highlighting additional design considerations and ethical tensions the auditor needs to be aware of so as not exacerbate or complement the harms propagated by the audited system.
Proceedings ArticleDOI
Perturbation Sensitivity Analysis to Detect Unintended Model Biases
TL;DR: A generic evaluation framework, Perturbation Sensitivity Analysis, is proposed, which detects unintended model biases related to named entities, and requires no new annotations or corpora to be employed.