arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1810.11367cs.CLcs.HCcs.LGstat.ML
收藏

LAMVI-2:一个比较和调整词嵌入模型的可视化工具

LAMVI-2: A Visual Tool for Comparing and Tuning Word Embedding Models

Xin Rong, Joshua Luckson, Eytan Adar

摘要:

调整机器学习模型,特别是深度学习架构,是一个复杂的过程。自动化超参数调整算法通常依赖于特定的优化指标。然而,在许多情况下,开发人员会将一个指标与另一个指标进行权衡:准确度与过拟合,精确度与召回率,较小的模型和准确度等。使用深度学习,不仅模型的表示不透明,当参数“旋钮”改变时,模型的行为也可能是不可预测的。因此,挑选“最佳”模型往往需要进行耗时的模型比较。在这项工作中,我们介绍了LAMVI-2,一个可视化的分析系统,以支持开发人员在比较超参数设置和结果。通过关注单词嵌入模型(“文本的深度学习”),我们整合了视图来比较高级统计数据和内部模型行为(例如,比较单词“距离”)。我们演示了开发人员如何使用LAMVI-2更快、更准确地缩小适当、有效的特定于应用程序的模型。

英文摘要:

Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one metric against another: accuracy versus overfitting, precision versus recall, smaller models and accuracy, etc. With deep learning, not only are the model's representations opaque, the model's behavior when parameters "knobs" are changed may also be unpredictable. Thus, picking the "best" model often requires time-consuming model comparison. In this work, we introduce LAMVI-2, a visual analytics system to support a developer in comparing hyperparameter settings and outcomes. By focusing on word-embedding models ("deep learning for text") we integrate views to compare both high-level statistics as well as internal model behaviors (e.g., comparing word 'distances'). We demonstrate how developers can work with LAMVI-2 to more quickly and accurately narrow down an appropriate and effective application-specific model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑