Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

no code implementations • 29 Oct 2022 • Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, Saleema Amershi

Large language models have demonstrated great potential to assist programmers in generating code.

Code Generation

Manipulating and Measuring Model Interpretability

1 code implementation • 21 Feb 2018 • Forough Poursabzi-Sangdeh, Daniel G. Goldstein, Jake M. Hofman, Jennifer Wortman Vaughan, Hanna Wallach

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models.

BIG-bench Machine Learning Decision Making +1

Evaluating Visual Representations for Topic Understanding and Their Effects on Manually Generated Topic Labels

no code implementations • TACL 2017 • Alison Smith, Tak Yeon Lee, Forough Poursabzi-Sangdeh, Jordan Boyd-Graber, Niklas Elmqvist, Leah Findlater

Probabilistic topic models are important tools for indexing, summarizing, and analyzing large document collections by their themes.

Topic Models

ALTO: Active Learning with Topic Overviews for Speeding Label Induction and Document Labeling

no code implementations • ACL 2016 • Forough Poursabzi-Sangdeh, Jordan Boyd-Graber, Leah Findlater, Kevin Seppi

Active Learning Topic Models

Speeding Document Annotation with Topic Models

no code implementations • NAACL 2015 • Forough Poursabzi-Sangdeh, Jordan Boyd-Graber

Document Classification General Classification +1