主題文件內人際互動關係擷取之研究

Abstract

由於Web2.0的發展，網際網路使用者處於資訊爆炸的時代。在面對大量文章的時候，先找出主題文件中人與人之間的互動關係將有助於閱讀者建立主題文件的背景架構以及對內容有初步的理解。為了找出人與人之間的互動關係，我們需要一個方法先辨別文字片段中是否有互動關係存在，接著再使用資訊擷取的演算法分析人物之間的互動關係，並且將同一主題文章中的人物建立其互動關係網路。 在這次的研究當中，我們將互動關係辨識定義成分類問題。結合句子中語法、語意和語境的資訊，設計出十九個語言的特徵來辨別文字片段當中是否有互動關係存在。實驗的結果顯示我們設計的互動關係辨識的方法是有效的，也優於其他著名的開放式資訊擷取系統。

Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract interaction tuples and construct an interaction network of topic persons. In this paper, we define interaction detection as a classification problem. The proposed interaction detection method, called FISER, exploits nineteen features covering syntactic, context-dependent, and semantic information in text to detect inter-sentential and iv intra-sentential interactive segments in topic documents. Empirical evaluations demonstrate that FISER outperforms many well-known open IE methods on identifying interactive segments in topic documents. In addition, the precision, recall and F1-score of the best feature combination are 72.6%, 55.6%, and 61.9% respectively.