Improving sentence simplification model with ordered neurons network

Sentence simplification is an essential task in natural language processing and aims to simplify complex sentences while retaining their primary meanings. To date, the main research works on sentence simplification models have been based on sequence‐to‐sequence (Seq2Seq) models. However, these Seq2S...

Full description

Saved in:
Bibliographic Details
Published in:CAAI Transactions on Intelligence Technology 2022-06, Vol.7 (2), p.268-277
Main Authors: Deng, Chunhui, Zhang, Lemin, Deng, Huifang
Format: Article
Language:English
Subjects:
Coders
Linear programming
Machine translation
Natural language processing
neural nets
Neural networks
Neurons
Sentences
Simplification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sentence simplification is an essential task in natural language processing and aims to simplify complex sentences while retaining their primary meanings. To date, the main research works on sentence simplification models have been based on sequence‐to‐sequence (Seq2Seq) models. However, these Seq2Seq models are incapable of analysing the hierarchical structure of sentences, which is of great significance for sentence simplification. The problem can be addressed with an ON‐MULTI‐STAGE model constructed based on the improved MULTI‐STAGE encoder model. In this model, an ordered neurons network is introduced and can provide sentence‐level structural information for the encoder and decoder. A weak attention connection method is then employed to make the decoder use the sentence‐level structural details. Experimental results on two open data sets demonstrated that the constructed model outperforms the state‐of‐the‐art baseline models in sentence simplification.
ISSN:2468-2322
2468-2322
DOI:10.1049/cit2.12047