Learning-Based Single-Document Summarization with Compression and 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.

ACL 2016

Cited by in corpus (13)

• A Deep Reinforced Model for Abstractive Summarization
• WikiHow: A Large Scale Text Summarization Dataset
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• Leveraging Lead Bias for Zero-shot Abstractive News Summarization
• Chinese Discourse Segmentation Using Bilingual Discourse Commonality
• AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
• Combining Word Embeddings and N-grams for Unsupervised Document Summarization
• Unsupervised Summarization by Jointly Extracting Sentences and Keywords
• Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
• A Novel ILP Framework for Summarizing Content with High Lexical Variety
• Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization