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
Applying Machine Learning to the Choice of Size Modifiers
TL;DR: A connection between the visible dimensions of objects and the kinds of language people use to refer to them is introduced, suggesting that people infer real world size features from images.
Proceedings ArticleDOI
SEAL : Interactive Tool for Systematic Error Analysis and Labeling
TL;DR: This paper introduces an interactive Systematic Error Analysis and Labeling (SEAL) tool that uses a two-step approach to identify high error slices of data and then in the second step introduce methods to give human-understandable semantics to those under-performing slices.
Proceedings Article
Prenominal Modifier Ordering via Multiple Sequence Alignment
TL;DR: A novel approach to producing a fluent ordering for a set of prenominal modifiers in a noun phrase is presented, adapting multiple sequence alignment techniques used in computational biology to the alignment of modifiers.
Patent
Metric for automatic assessment of conversational responses
Michel Galley,Alessandro Sordoni,Chris Brockett,Jianfeng Gao,William B. Dolan,Yangfeng Ji,Michael Auli,Margaret Mitchell,Chris Quirk +8 more
TL;DR: In this article, a response assessment engine generates a metric score for a machine-generated response based on an assessment metric and the set of multi-reference responses, and the metric score indicates a quality of the machine generated conversational response relative to a user-generated message and a context of the user generated message.
Proceedings Article
Semi-Supervised Modeling for Prenominal Modifier Ordering
TL;DR: It is argued that ordering prenominal modifiers -- typically pursued as a supervised modeling task -- is particularly well-suited to semi-supervised approaches, and by relying on automatic parses to extract noun phrases, can scale up the training data by orders of magnitude.