Split and Rephrase

Abstract : 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 labelers 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 tu-ples mapping a single complex sentence to a sequence of sentences expressing the same meaning. 1 Second, we propose five models (vanilla sequence-to-sequence to semantically-motivated models) to understand the difficulty of the proposed task.
Document type :
Conference papers
Complete list of metadatas

Cited literature [59 references]  Display  Hide  Download

https://hal.inria.fr/hal-01623746
Contributor : Claire Gardent <>
Submitted on : Wednesday, October 25, 2017 - 4:11:22 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on : Friday, January 26, 2018 - 3:22:12 PM

File

2017-EMNLP-shashi.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01623746, version 1

Citation

Shashi Narayan, Claire Gardent, Shay Cohen, Anastasia Shimorina. Split and Rephrase. EMNLP 2017: Conference on Empirical Methods in Natural Language Processing, Sep 2017, Copenhagen, Denmark. pp.617 - 627. ⟨hal-01623746⟩

Share

Metrics

Record views

586

Files downloads

122