Joint Parsing and Generation for Abstractive Summarization

TL;DR

This paper introduces a neural model that jointly generates summaries and their syntactic parses to improve grammaticality and fidelity to the original content in abstractive summarization.

Contribution

It proposes a novel neural architecture combining sequential and tree-based decoders for joint summarization and parsing, along with a new human evaluation protocol.

Findings

Achieves competitive results on multiple datasets.

Improves grammaticality and faithfulness of summaries.

Introduces a new evaluation method for summary fidelity.

Abstract

Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its syntactic dependency parse while performing abstraction. If generating a word can introduce an erroneous relation to the summary, the behavior must be discouraged. The proposed method thus holds promise for producing grammatical sentences and encouraging the summary to stay true-to-original. Our contributions of this work are twofold. First, we present a novel neural architecture for abstractive summarization that combines a sequential decoder with a tree-based decoder in a synchronized manner to generate a summary sentence and its syntactic parse. Secondly, we describe a novel human evaluation protocol to assess if, and to what extent, a summary remains true to its original meanings. We evaluate our method on a number of summarization datasets and demonstrate competitive results against strong baselines.