【正文】 relationship mining. Focusing on these three key problems, this dissertation proposes a statistical unsupervised learning framework named StatSnowball, which has overe the disadvantage of stateoftheart unsupervised learning models. The main contents and contributions of this dissertation are as follows: 1. Discuss the stateoftheart Webscale knowledge mining systems. Mainly focus on supervised methods based on the natural language features and the stateoftheart selfsupervised methods based on the extraction patterns. These methods have been widely used in different tasks of knowledge mining. The emphasis of our analysis is the basic idea behind these two types of methods, and typical models. 2. Propose an unsupervised learning model: StatSnowball (Statistical Snowball) for the relationship extraction. Our model adopts the bootstrapping framework and uses the general statistical model Markov logic works as the underlying extraction model. By using the statistical pattern evaluation and selection me thods, StatSnowball can incorporate all kinds of patterns. By adopting MLN, StatSnowball acplishes various levels of joint inference in relationship Abstract V extraction. Experiments on both small but fully labeled data and large scale Web data have shown the effectiveness of our methods. 3. Propose a uniform named entity recognition and relation extraction model based on iterative framework: EntSum. Our model extends conditional random field model used by named entity recognition, which enables relationship features to be added to the model. Joint model adopts the iterative framework to build bidirectional connection between two tasks, in which both results can be used in the other’s decision making process. Experiments on the real Web data have shown the increase to the performance on both two tasks. 4. Propose an entity summarization model: BioSnowball, which can be considered as an extension to the basic StatSnowball model. By using the FactBio duality, BioSnowball adopts the bootstrapping framework, and starts from only a small set of samples to jointly plete two different types of summarization. Our model can jointly plete the fact extraction and biography ranking for Web entities. Experiments on the real Web data and the user study have s hown the effectiveness of our model on both problems. The success of BioSnowball has also shown the generality of the basic StatSnowball model. 5. Build two public available named entity search engines named Renlifang and EntityCube, which the author has participated in as the main researcher and developer. These two search engines automatically mine knowledge from billions of Chinese and English Web pages respectively and build an entry page for every extracted entity. StatSnowball has been already applied to the system, and other methods in this dissertation have also been verified under the data of these two real systems. At the end of this dissertation, we conclude it and prospect the further studies in the future. Key Words: knowledge mining, named entity search, selfsupervised learning, relationship extraction, named entity recognition, named entity summarization 目 錄 VI 目 錄 摘 要 .................................................................................................... II ABSTRACT .......................................................................................... IV 目 錄 ................................................................................................... VI 圖表目錄及縮略語 ................................................................................ X 插圖目錄 ................................................................................................................... X 表格目錄 .................................................................................................................. XI 第 1 章 緒論 ........................................................................................... 1 研究背景與研究意義 ......................................................................................... 1 研究背景 ......................................................................................................... 1 研究意義 ......................................................................................................... 4 關鍵問題與研究任務 ......................................................................................... 6 關鍵問題 ......................................................................................................... 6 研究任務 ......................................................................................................... 7 研究內(nèi)容與結構安排 ......................................................................................... 8 第 2 章 統(tǒng)計滾雪球模型 ...................................................................... 11 簡介 ................................................................................................................... 11 關系抽取任務介紹 ......................................................................................... 11 相關工作 ....................................................................................................... 13 統(tǒng)計滾雪球模型架構 ....................................................................................... 14 關系抽取問題定義 ......................................................................................... 14 統(tǒng)計滾雪球模型架構 ..................................................................................... 15 關系抽取統(tǒng)計模型 ........................................................................................... 18 馬爾可夫邏輯網(wǎng)絡 ......................................................................................... 18 聯(lián)合推理 ....................................................................................................... 21 目 錄 VII 加速方法 ...........................