Recently, much research focuses on event storyline generation, which aims to produce a concise, global and temporal event summary from a collection of articles.Generally, each event contains multiple sub-events and the storyline should be composed by the component summaries of all the sub-events.However, different sub-events have different part-whole relationship with the major event, which is important to correspond to users' interests but seldom considered in previous work.To distinguish different types of sub-events, we propose a mixture-event-aspect model which models different sub-events into local and global aspects.Combining these local/global aspects with summarization requirements together, we utilize an optimization method to generate the component summaries along the timeline.We develop experimental systems on 6 distinctively different datasets.Evaluation and comparison results indicate the effectiveness of our proposed method.

Query-oriented relevance, information richness and novelty are important requirements in query-focused summarization, which, to a considerable extent, determine the summary quality. Previous work either rarely took into account all above demands simultaneously or dealt with part of them in the dynamic process of choosing sentences to generate a summary. In this paper, we propose a novel approach that integrates all these requirements skillfully by treating them as sentence features, making that the finally generated summary could fully reflect the combinational effect of these properties. Experimental results on the DUC2005 and DUC2006 datasets demonstrate the effectiveness of our approach.

The clustering of topic-related web pages has been recognized as a foundational work in exploiting large sets of web pages such as the cases in search engines and web archive systems, which collect and preserve billions of web pages. However, this task faces great challenges both in efficiency and accuracy. In this paper we present a novel clustering algorithm for large scale topical web pages which achieves high efficiency together with considerately high accuracy. In our algorithm, a two-phase divide and conquer framework is developed to solve the efficiency problem, in which both link analysis and content analysis are utilized in mining the topical similarity between pages to achieve a high accuracy. A comprehensive experiment was conducted to evaluate our method in terms of its effectiveness, efficiency, and quality of result.

To find near-duplicate documents, fingerprint-based paradigms such as Broder's shingling and Charikar's simhash algorithms have been recognized as effective approaches and are considered the state-of-the-art. Nevertheless, we see two aspects of these approaches which may be improved. First, high score under these algorithms' similarity measurement implies high probability of similarity between documents, which is different from high similarity of the documents. But how similar two documents are is what we really need to know. Second, there has to be a tradeoff between hash-code length and hash-code multiplicity in fingerprint paradigms, which makes it hard to maintain a satisfactory recall level while improving precision.

In this paper, we describe an experimental search engine on our Chinese web archive since 2001. The original data set contains nearly 3 billion Chinese web pages crawled from past 5 years. From the collection, 430 million "article-like" pages are selected and then partitioned into 68 million sets of similar pages. The titles and publication dates are determined for the pages. An index is built. When searching, the system returns related pages in a chronological order. This way, if a user is interested in news reports or commentaries for certain previously happened event, he/she will be able to find a quite rich set of highly related pages in a convenient way.