Split and Rephrase

By Claire Gardent, Shay B. Cohen, Anastasia Shimorina. 2017

100 citations recorded by the source corpus.

We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences. Like sentence simplification, splitting-and-rephrasing has the potential of benefiting both natural language processing and societal applications. Because shorter sentences are generally better processed by NLP systems, it could be used as a preprocessing step which facilitates and improves the performance of parsers, semantic role labellers and machine translation systems. It should also be of use for people with reading disabilities because it allows the conversion of longer sentences into shorter ones. This paper makes two contributions towards this new task. First, we create and make available a benchmark consisting of 1,066,115 tuples mapping a single complex sentence to a sequence of sentences expressing the same meaning. Second, we propose five models (vanilla sequence-to-sequence to semantically-motivated models) to understand the difficulty of the proposed task.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

The WebNLG Challenge: Generating Text from RDF Data (2017, methodology): “As explained in (Narayan et al., 2017), this dataset was created using the meaning represen-6 tations (sets of RDF triples) as pivot.”
Leveraging Pre-trained Checkpoints for Sequence Generation Tasks (2019, background): “sentence into two ormore coherent short sentences (Narayan et al., 2017).”
Joint Parsing and Generation for Abstractive Summarization (2019, methodology): “In this work we present a novel use of a newly released dataset—WebSplit (Narayan et al. 2017).”
Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue (2019, background): “Other work in generation addresses tasks such as rephrasals for generating paraphrases (Prakash et al., 2016; Gupta et al., 2018), sentence simpliﬁ-cation (Narayan et al., 2017), and query rewriting for question answering (Dong et al., 2017).”
Policy Compliance Detection via Expression Tree Inference (2022, methodology): “We employ a split-and-rephrase (Narayan et al., 2017) text simpliﬁcation approach in order train a text-to-text model to split policies into their constituent spans while preserving their meaning, so as to extract appropriate and well-formed spans.”
BLEU is Not Suitable for the Evaluation of Text Simplification (2018, methodology): “While BLEU is standardly used for TS evaluation (e.g., Xu et al., 2016; Nisioi et al., 2017; Zhang and Lapata, 2017; Ma and Sun, 2017), only few works tested its correlation with human judgments.”