Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints

TL;DR

This paper introduces a discriminative model for single-document summarization that combines compression and anaphoricity constraints, improving summary quality by ensuring coherence and relevance through learned features and dependency rules.

Contribution

The work presents a novel integrated framework that jointly models compression and anaphoricity constraints, trained end-to-end for enhanced summarization performance.

Findings

Outperforms prior models on ROUGE scores

Achieves higher human judgment scores of linguistic quality

Effectively maintains coherence through anaphoricity constraints

Abstract

We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints. Our model selects textual units to include in the summary based on a rich set of sparse features whose weights are learned on a large corpus. We allow for the deletion of content within a sentence when that deletion is licensed by compression rules; in our framework, these are implemented as dependencies between subsentential units of text. Anaphoricity constraints then improve cross-sentence coherence by guaranteeing that, for each pronoun included in the summary, the pronoun's antecedent is included as well or the pronoun is rewritten as a full mention. When trained end-to-end, our final system outperforms prior work on both ROUGE as well as on human judgments of linguistic quality.