Angler: Helping Machine Translation Practitioners Prioritize Model Improvements

Autor:	Robertson, Samantha, Wang, Zijie J., Moritz, Dominik, Kery, Mary Beth, Hohman, Fred
Rok vydání:	2023
Předmět:	Computer Science - Human-Computer Interaction Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
DOI:	10.1145/3544548.3580790
Popis:	Machine learning (ML) models can fail in unexpected ways in the real world, but not all model failures are equal. With finite time and resources, ML practitioners are forced to prioritize their model debugging and improvement efforts. Through interviews with 13 ML practitioners at Apple, we found that practitioners construct small targeted test sets to estimate an error's nature, scope, and impact on users. We built on this insight in a case study with machine translation models, and developed Angler, an interactive visual analytics tool to help practitioners prioritize model improvements. In a user study with 7 machine translation experts, we used Angler to understand prioritization practices when the input space is infinite, and obtaining reliable signals of model quality is expensive. Our study revealed that participants could form more interesting and user-focused hypotheses for prioritization by analyzing quantitative summary statistics and qualitatively assessing data by reading sentences. Comment: Accepted to CHI 2023. 20 pages, 6 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.05967 Zobrazit plný text záznamu View this record from Arxiv