Specificity-Based Sentence Ordering for Multi-Document Extractive Risk Summarization

TL;DR

This paper introduces a novel sentence ordering method for multi-document extractive summarization in risk mining, leveraging shifts in specificity to improve summary quality and readability without complex NLP.

Contribution

It proposes a new selection algorithm that alternates extracts based on curated or autoencoded key terms to enhance summary coherence and informativeness.

Findings

Outperforms non-alternating summaries on ROUGE and BLEU scores

Achieves comparable quality to human summaries in manual evaluations

Induces effective shifts in specificity without complex NLP techniques

Abstract

Risk mining technologies seek to find relevant textual extractions that capture entity-risk relationships. However, when high volume data sets are processed, a multitude of relevant extractions can be returned, shifting the focus to how best to present the results. We provide the details of a risk mining multi-document extractive summarization system that produces high quality output by modeling shifts in specificity that are characteristic of well-formed discourses. In particular, we propose a novel selection algorithm that alternates between extracts based on human curated or expanded autoencoded key terms, which exhibit greater specificity or generality as it relates to an entity-risk relationship. Through this extract ordering, and without the need for more complex discourse-aware NLP, we induce felicitous shifts in specificity in the alternating summaries that outperform non-alternating summaries on automatic ROUGE and BLEU scores, and manual understandability and preferences evaluations - achieving no statistically significant difference when compared to human authored summaries.