A Cosine Maximization-Minimization approach for User-Oriented Multi-Document Update Summarization
نویسندگان
چکیده
This paper presents a User-Oriented MultiDocument Update Summarization system based on a maximization-minimization approach. Our system relies on two main concepts. The first one is the cross summaries sentence redundancy removal which tempt to limit the redundancy of information between the update summary and the previous ones. The second concept is the newness of information detection in a cluster of documents. We try to adapt the clustering technique of bag of words extraction to a topic enrichment method that extend the topic with unique information. In the DUC 2007 update evaluation, our system obtained very good results in both automatic and human evaluations.
منابع مشابه
Complex Question Answering: Unsupervised Learning Approaches and Experiments
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topic-oriented, informative multi-document summarization where the goal is to produce a single text as a compressed version of a set of documents with a minimum loss of relevant information. In this paper, we experiment with one empirical method and two unsupervised statistic...
متن کاملAn Effective Sentence Ordering Approach For Multi-Document Summarization Using Text Entailment
With the rapid development of modern technology electronically available textual information has increased to a considerable amount. Summarization of textual information manually from unstructured text sources creates overhead to the user, therefore a systematic approach is required. Summarization is an approach that focuses on providing the user with a condensed version of the original text bu...
متن کاملThe LIA summarization system at DUC-2007
This paper presents the LIA summarization systems participating to DUC 2007. This is the second participation of the LIA at DUC and we will discuss our systems in both main and update tasks. The system proposed for the main task is the combination of seven different sentence selection systems. The fusion of the system outputs is made with a weighted graph where the cost functions integrate the ...
متن کاملSelecting Sentences for Answering Complex Questions
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. In this paper, we have experimented with one empirical and two unsupervised statistical machine learning techniques: kmeans and Expectation Maximization (EM), for computing relative importance of the sentences. However,...
متن کاملNEO-CORTEX: A Performant User-Oriented Multi-Document Summarization System
This paper discusses an approach to topic-oriented multidocument summarization. It investigates the effectiveness of using additional information about the document set as a whole, as well as individual documents. We present NEO-CORTEX, a multi-document summarization system based on the existing CORTEX system. Results are reported for experiments with a document base formed by the NIST DUC-2005...
متن کامل