應用自然語言處理技術分析文學小說角色 之關係：以互動視覺化呈現;Natural Language Processing applied to Interactive Character Relationships Visualization in Novels

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/84105

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/84105

Title:	應用自然語言處理技術分析文學小說角色之關係：以互動視覺化呈現;Natural Language Processing applied to Interactive Character Relationships Visualization in Novels
Authors:	亞瑟;Amalvy, Arthur
Contributors:	資訊工程學系
Keywords:	自然語言處理;數字人文科學;角色知識圖;Natural Language Processing;Digital Humanities;Character Networks;Automatic Quote Attribution
Date:	2020-08-04
Issue Date:	2020-09-02 18:05:05 (UTC+8)
Publisher:	國立中央大學
Abstract:	文學作品對人類文化具有深遠的影響，因此在歷史演進過程中，人們對文學作品進行大量且廣泛的研究。在這些作品中，角色們之間的關係常為作品核心。對於人物關係的探討，我們可視為研究其網路架構；意即使用圖形網路來表示角色關係。由於角色之間對話的重要性，我們可根據其內容抽取特殊的網路，稱對話網路，該網路僅透過角色之間的談話而生成。可以透過圖論或是資訊學領域的相關工具進行此研究，分析並挖掘傳統文學背後的涵義。本研究致力於對動態權重的對話網路研發新的自動化抽取方式。我們首先提出一種關於此類型網絡的通用辦法，並將其應用於文學小說。基於該應用，本研究提出了一種新的自動話語歸因方法。最後，我們開發一款簡易的網路視覺化工具，藉由此工具，我們可以針對所抽取的特徵網路，進行更深入的分析。;Due to their importance in humanity culture, literary works have been extensively studied during the course of history. In those works, characters and their relationships often play a central role. The study of the structure of those relationships is the study of character networks : that is, a special kind of graph that can be used to represent these structures. Due to the importance of dialogue between characters, one can extract a specialised kind of network : a conversational network, extracted using only dialogues between characters. Using tools from graph theory or other fields of computer science, those networks can be studied to reveal original insights unattainable fromtraditional literary analysis. This work is dedicated to the automatic extraction of dynamic signed conversational networks. We propose a general method to extract those kinds of networks, that can be used in any type of work. We then show an example where we apply this method on novels in particular, which makes us propose a new technique for automatic utterance attribution. Lastly, we create a simple example of software allowing the visualization of extracted networks to analyze them.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	125	View/Open

社群 sharing

Loading...