ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences

TL;DR

This paper introduces ABCD, a graph-based neural framework for decomposing complex sentences into simple, atomic sentences, enhancing understanding for NLP tasks with a new dataset and improved accuracy over baselines.

Contribution

The paper presents a novel graph edit approach for sentence decomposition, a new dataset DeSSE, and demonstrates improved performance over traditional parsing methods.

Findings

ABCD achieves comparable performance to parsing baselines on MinWiki.

On DeSSE, ABCD outperforms encoder-decoder models in atomic sentence count accuracy.

The approach enables effective complex sentence decomposition with detailed error analysis.

Abstract

Atomic clauses are fundamental text units for understanding complex sentences. Identifying the atomic sentences within complex sentences is important for applications such as summarization, argument mining, discourse analysis, discourse parsing, and question answering. Previous work mainly relies on rule-based methods dependent on parsing. We propose a new task to decompose each complex sentence into simple sentences derived from the tensed clauses in the source, and a novel problem formulation as a graph edit task. Our neural model learns to Accept, Break, Copy or Drop elements of a graph that combines word adjacency and grammatical dependencies. The full processing pipeline includes modules for graph construction, graph editing, and sentence generation from the output graph. We introduce DeSSE, a new dataset designed to train and evaluate complex sentence decomposition, and MinWiki, a subset of MinWikiSplit. ABCD achieves comparable performance as two parsing baselines on MinWiki. On DeSSE, which has a more even balance of complex sentence types, our model achieves higher accuracy on the number of atomic sentences than an encoder-decoder baseline. Results include a detailed error analysis.