Summarizing Encyclopedic Term Descriptions on the Web

TL;DR

This paper presents an automatic summarization method that consolidates multiple web-based descriptions of a term into a single, concise encyclopedic summary, enhancing the coherence and comprehensiveness of web-derived content.

Contribution

It introduces a novel summarization approach that combines multiple web descriptions into a unified, encyclopedic text, improving upon previous independent paragraph extraction methods.

Findings

The method effectively produces concise summaries from diverse descriptions.

Experimental results demonstrate improved coherence and informativeness.

The approach outperforms baseline methods in summarization quality.

Abstract

We are developing an automatic method to compile an encyclopedic corpus from the Web. In our previous work, paragraph-style descriptions for a term are extracted from Web pages and organized based on domains. However, these descriptions are independent and do not comprise a condensed text as in hand-crafted encyclopedias. To resolve this problem, we propose a summarization method, which produces a single text from multiple descriptions. The resultant summary concisely describes a term from different viewpoints. We also show the effectiveness of our method by means of experiments.