Improving sentence simplification model with ordered neurons network
Abstract 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, th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12047 |
| _version_ | 1811283171391569920 |
|---|---|
| author | Chunhui Deng Lemin Zhang Huifang Deng |
| author_facet | Chunhui Deng Lemin Zhang Huifang Deng |
| author_sort | Chunhui Deng |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-04-13T02:06:40Z |
| format | Article |
| id | doaj.art-fdff9d705393450bafbe9dfe6ea07343 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-04-13T02:06:40Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-fdff9d705393450bafbe9dfe6ea073432022-12-22T03:07:28ZengWileyCAAI Transactions on Intelligence Technology2468-23222022-06-017226827710.1049/cit2.12047Improving sentence simplification model with ordered neurons networkChunhui Deng0Lemin Zhang1Huifang Deng2School of Computer Engineering Guangzhou College of South China University of Technology Guangzhou ChinaSchool of Computer Science and Engineering South China University of Technology Guangzhou ChinaSchool of Computer Science and Engineering South China University of Technology Guangzhou ChinaAbstract 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.https://doi.org/10.1049/cit2.12047neural netsnatural language processing |
| spellingShingle | Chunhui Deng Lemin Zhang Huifang Deng Improving sentence simplification model with ordered neurons network CAAI Transactions on Intelligence Technology neural nets natural language processing |
| title | Improving sentence simplification model with ordered neurons network |
| title_full | Improving sentence simplification model with ordered neurons network |
| title_fullStr | Improving sentence simplification model with ordered neurons network |
| title_full_unstemmed | Improving sentence simplification model with ordered neurons network |
| title_short | Improving sentence simplification model with ordered neurons network |
| title_sort | improving sentence simplification model with ordered neurons network |
| topic | neural nets natural language processing |
| url | https://doi.org/10.1049/cit2.12047 |
| work_keys_str_mv | AT chunhuideng improvingsentencesimplificationmodelwithorderedneuronsnetwork AT leminzhang improvingsentencesimplificationmodelwithorderedneuronsnetwork AT huifangdeng improvingsentencesimplificationmodelwithorderedneuronsnetwork |