CLAIIROct 24, 2018

Effective extractive summarization using frequency-filtered entity relationship graphs

arXiv:1810.10419v15 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of generating more coherent and informative summaries for users of text summarization tools, though it is incremental in nature.

The paper tackled the limitations of word-frequency-based extractive summarization, such as ignoring context and uneven topic coverage, by developing a hybrid model that combines word-frequency with entity relationship graphs. The result was a method competitive by ROUGE standards and moderately more informative summaries, as rated by 94 human evaluators.

Word frequency-based methods for extractive summarization are easy to implement and yield reasonable results across languages. However, they have significant limitations - they ignore the role of context, they offer uneven coverage of topics in a document, and sometimes are disjointed and hard to read. We use a simple premise from linguistic typology - that English sentences are complete descriptors of potential interactions between entities, usually in the order subject-verb-object - to address a subset of these difficulties. We have developed a hybrid model of extractive summarization that combines word-frequency based keyword identification with information from automatically generated entity relationship graphs to select sentences for summaries. Comparative evaluation with word-frequency and topic word-based methods shows that the proposed method is competitive by conventional ROUGE standards, and yields moderately more informative summaries on average, as assessed by a large panel (N=94) of human raters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes