用於理解和比較變壓器模型的可視化分析系統

dc.contributor王科植zh_TW
dc.contributorWang, Ko-Chihen_US
dc.contributor.author吳建霖zh_TW
dc.contributor.authorWu, Jian-Linen_US
dc.date.accessioned2023-12-08T08:02:44Z
dc.date.available2022-09-20
dc.date.available2023-12-08T08:02:44Z
dc.date.issued2022
dc.description.abstract近年來,自然語言處理(NLP)技術取得了長足的進步。基於轉換器的模型在 各種自然語言處理問題中表現良好。然而,一個自然語言任務可以由多個不同的模 型來完成,它們的架構略有不同,例如不同的層數和注意力頭。除了量化指標作為 選擇模型的依據外,很多用戶還考慮了理解模型語言的能力以及它所需要的計算資 源。然而,對兩個不同層數和注意力頭的基於transformer的模型進行比較和深入的 分析並不容易,因為它缺乏模型之間固有的一對一匹配。因此,當用戶為NLP 任務 訓練、選擇或改進模型時,比較具有不同架構的模型是一項至關重要且具有挑戰性 的任務。在本文中,我們提出了一個可視化分析系統來探索語言模型之間的差異, 並幫助用戶選擇模型或找出模型可以改進的地方。我們的系統支持兩個模型的比 較,用戶可以交互地探索不同模型下的特定層或頭部,並識別異同。使用我們的工 具,用戶不僅可以通過模型學習到哪些語言特徵,還可以深入分析兩個不同層數和 頭的基於轉換器的模型之間的細微差別。用戶的用例和反饋表明,我們的工具可以 幫助人們深入了解並促進模型比較任務。zh_TW
dc.description.abstractIn recent years, natural language processing (NLP) technology has made great progress. Models based on transformers have performed well in various natural language processing problems. However, a natural language task can be done by multiple different models with slightly difference architectures, such as different number of layers and attention heads. In addition to quantitative indicators as the basis for selecting models, many users also consider the ability of understanding the language of the model and the computing resources it requires. However, comparably and deeply analyze two transformer-based models with difference number of layers and attention heads are not easy because it is lacks of the inherent one to one match between models. So comparing models with different architectures is a crucial and challenging task when users train, select or improve models for their NLP tasks. In this paper, we propose a visual analysis system to explore the differences between language models and help user to select model or find out where the model could be improve. Our system supports the comparison of two models and users can interactively explore specific layers or heads under different models and identify the similarities or differences. With our tool, users can not only what linguistic features are learned by the model, but also deeply analyze the subtle difference between two transformer-based model with different number of layers and heads. The use cases and feedback from users show that our tool can help people gain insight into and facilitate model comparison task.en_US
dc.description.sponsorship資訊工程學系zh_TW
dc.identifier60947092S-42318
dc.identifier.urihttps://etds.lib.ntnu.edu.tw/thesis/detail/e39c0ab71ec5697fa904294716cbf12e/
dc.identifier.urihttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/121607
dc.language英文
dc.subjectnonezh_TW
dc.subjectVisualizationen_US
dc.subjectTransformeren_US
dc.title用於理解和比較變壓器模型的可視化分析系統zh_TW
dc.titleA Visual Analytics System for Understanding and Comparing Transformer Modelsen_US
dc.typeetd

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
202200042318-104628.pdf
Size:
4.02 MB
Format:
Adobe Portable Document Format
Description:
etd

Collections