IMASS：智慧型微網誌自動分析及摘要系統

Abstract

本論文提出一個自動摘要系統，針對每一則微網誌上的訊息及回應產生簡明易讀的摘要。此系統的目的在於幫助微網誌使用者可以在大量的網路訊息中，有效率地擷取到重要且有意義的資訊。它採用了兩階段的摘要架構：第一個階段進行訊息的分類。每一則訊息都會被分為「疑問」、「連結分享」、「連結討論」以及「閒聊」等四種類型；第二個階段則是針對該訊息在上個階段被分配到的類別，採用適合該類的摘要策略及呈現方式。我們提出的策略共有「意見分析」、「回應分群」以及「回應相關度偵測」等三種。本論文在處理微網誌摘要的問題上，提出了一個不同於傳統文件摘要技術的觀點：透過不同系統之間的整合，電腦可以有能力產生出合於使用者目的之摘要，而不僅是訊息的過濾與壓縮。

This paper presents a system to summarize a microblog post and its responses with the goal to provide readers a more constructive and concise set of information for efficient digestion. We introduce a novel two-phase summarization scheme. In the first phase, the post plus its responses are classified into four categories based on the intention, Interrogation, URL-Sharing, URL-Discussion and Chat. For each type of post, in the second phase, we exploit different strategies, including Opinion Analysis, Response Group Clustering, and Response Relevancy Detection, to summarize and highlight critical information to display. This system provides an alternative thinking about machine-summarization: by utilizing AI approaches, computers are capable of constructing deeper and more user-friendly abstraction.