StructSum: Incorporating Latent and Explicit Sentence Dependencies for Single Document Summarization

03/01/2020
by   Vidhisha Balachandran, et al.
0

Traditional preneural approaches to single document summarization relied on modeling the intermediate structure of a document before generating the summary. In contrast, the current state of the art neural summarization models do not preserve any intermediate structure, resorting to encoding the document as a sequence of tokens. The goal of this work is two-fold: to improve the quality of generated summaries and to learn interpretable document representations for summarization. To this end, we propose incorporating latent and explicit sentence dependencies into single-document summarization models. We use structure-aware encoders to induce latent sentence relations, and inject explicit coreferring mention graph across sentences to incorporate explicit structure. On the CNN/DM dataset, our model outperforms standard baselines and provides intermediate latent structures for analysis. We present an extensive analysis of our summaries and show that modeling document structure reduces copying long sequences and incorporates richer content from the source document while maintaining comparable summary lengths and an increased degree of abstraction.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/22/2018

Neural Latent Extractive Document Summarization

Extractive summarization models need sentence level labels, which are us...
research
11/17/2022

Abstractive Summarization Guided by Latent Hierarchical Document Structure

Sequential abstractive neural summarizers often do not use the underlyin...
research
09/21/2022

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

Current abstractive summarization models either suffer from a lack of cl...
research
03/29/2016

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

We present a discriminative model for single-document summarization that...
research
04/13/2022

FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations

Despite recent improvements in abstractive summarization, most current a...
research
05/20/2018

A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)

The recent advance in neural network architecture and training algorithm...
research
03/26/2019

Document Similarity for Texts of Varying Lengths via Hidden Topics

Measuring similarity between texts is an important task for several appl...

Please sign up or login with your details

Forgot password? Click here to reset