![](/images/graphics-bg.png)
A Deep Paraphrase Identification Model Interacting Semantics with Syntax
Joint Authors
Han, Yong
Kong, Leilei
Han, Zhongyuan
Qi, Haoliang
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-14, 14 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-10-30
Country of Publication
Egypt
No. of Pages
14
Main Subjects
Abstract EN
Paraphrase identification is central to many natural language applications.
Based on the insight that a successful paraphrase identification model needs to adequately capture the semantics of the language objects as well as their interactions, we present a deep paraphrase identification model interacting semantics with syntax (DPIM-ISS) for paraphrase identification.
DPIM-ISS introduces the linguistic features manifested in syntactic features to produce more explicit structures and encodes the semantic representation of sentence on different syntactic structures by means of interacting semantics with syntax.
Then, DPIM-ISS learns the paraphrase pattern from this representation interacting the semantics with syntax by exploiting a convolutional neural network with convolution-pooling structure.
Experiments are conducted on the corpus of Microsoft Research Paraphrase (MSRP), PAN 2010 corpus, and PAN 2012 corpus for paraphrase plagiarism detection.
The experimental results demonstrate that DPIM-ISS outperforms the classical word-matching approaches, the syntax-similarity approaches, the convolution neural network-based models, and some deep paraphrase identification models.
American Psychological Association (APA)
Kong, Leilei& Han, Zhongyuan& Han, Yong& Qi, Haoliang. 2020. A Deep Paraphrase Identification Model Interacting Semantics with Syntax. Complexity،Vol. 2020, no. 2020, pp.1-14.
https://search.emarefa.net/detail/BIM-1145816
Modern Language Association (MLA)
Kong, Leilei…[et al.]. A Deep Paraphrase Identification Model Interacting Semantics with Syntax. Complexity No. 2020 (2020), pp.1-14.
https://search.emarefa.net/detail/BIM-1145816
American Medical Association (AMA)
Kong, Leilei& Han, Zhongyuan& Han, Yong& Qi, Haoliang. A Deep Paraphrase Identification Model Interacting Semantics with Syntax. Complexity. 2020. Vol. 2020, no. 2020, pp.1-14.
https://search.emarefa.net/detail/BIM-1145816
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1145816