Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion

Abstract

In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems. AbstractIn recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems.

Automatic Summarization

“…It relies only on word probability to calculate importance [212]. For each sentence S j in the input it assigns a weight equal to the average probability p(w i ) of the content words in the sentence, estimated from the input for summarization:…”

Text Summarization Techniques: A Brief Survey

“…Vanderwende et al [19] proposed the SumBasic system which uses only the word probability approach to determine sentence importance. For each sentence, S j , in the input, it assigns a weight equal to the average probability of the words in the sentence:…”

Single-document and multi-document summarization techniques for email threads using sentence compression

“…The advantage of this approach is that it provides the necessary flexibility to accommodate complex interactions between relevance and redundancy that cannot be captured in a single compression. Downstream processes that have access to more information are capable of making better decisions on the choice of a final compression; this approach is also espoused by Vanderwende et al (2006).…”