A deep network model for paraphrase detection in short text messages
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Recognizing this importance, we study in particular how to address the challenges with detecting paraphrases in user generated short texts, such as Twitter, which often contain language irregularity and noise, and do not necessarily contain as much semantic information as longer clean texts. We propose a novel deep neural network-based approach that relies on coarse-grained sentence modelling using a convolutional neural network (CNN) and a recurrent neural network (RNN) model, combined with a specific fine-grained word-level similarity matching model. More specifically, we develop a new architecture, called DeepParaphrase, which enables to create an informative semantic representation of each sentence by (1) using CNN to extract the local region information in form of important n-grams from the sentence, and (2) applying RNN to capture the long-term dependency information. In addition, we perform a comparative study on state-of-the-art approaches within paraphrase detection. An important insight from this study is that existing paraphrase approaches perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts, and vice versa. In contrast, our evaluation has shown that the proposed DeepParaphrase-based approach achieves good results in both types of texts, thus making it more robust and generic than the existing approaches.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Enriching Word Vectors with Subword Information
Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00051 · Cited by 9,645 · cited 1×
“Recently, deep learning-based methods have shifted researchers’ attention towards semantically distributed representations [13, 14, 15].”
BackgroundADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Character-Aware Neural Language Models
Kim, Y., Jernite, Y., Sontag, D., & Rush, A. M. (2015) · arXiv · doi:10.48550/arxiv.1508.06615 · Cited by 1,530
Kiros, R., Zhu, Y., Salakhutdinov, R., Zemel, R. S., Torralba, A., Urtasun, R., & Fidler, S. (2015) · arXiv · doi:10.48550/arxiv.1506.06726 · Cited by 1,293 · cited 1×
“Recurrent neural networks (RNNs) are able to learn the long-term dependencies in sequential data and that has also been used in the literature for representing the text [17].”
BackgroundUnsupervised construction of large paraphrase corpora: exploiting massively parallel news sources
Dolan, B., Quirk, C., & Brockett, C. (2004) · Proceedings of the 20th international conference on Computational Linguistics - COLING '04 · doi:10.3115/1220355.1220406 · Cited by 728 · cited 1×
“Most of the existing paraphrase systems have performed quite well on clean text corpora, such as the Microsoft Paraphrase Corpus (MSRP) [1].”
Method
Research works printed but not linked: 14
- AL-Smadi, 2017, Paraphrase identification and semantic text similarity analysis in arabic news tweets using lexical, syntactic, and semantic features, Information Processing and Management, 53, 640, 10.1016/j.ipm.2017.01.002 · DOI
- Collobert, 2011, Natural language processing (almost) from scratch, Journal of Machine Learning Research, 12, 2493
- El-Alfy, 2015, Boosting paraphrase detection through textual similarity metrics with abductive networks, Applied Soft Computing, 26, 444, 10.1016/j.asoc.2014.10.021 · DOI
- Ferreira, 2018, Combining sentence similarities measures to identify paraphrases, Computer Speech and Language, 47, 59, 10.1016/j.csl.2017.07.002 · DOI
- Franco-Salvador, 2016, A systematic study of knowledge graph analysis for cross-language plagiarism detection, Information Processing and Management, 52, 550, 10.1016/j.ipm.2015.12.004 · DOI
- Jiang, 2017, Wikipedia-based information content and semantic similarity computation, Information Processing and Management, 53, 248, 10.1016/j.ipm.2016.09.001 · DOI
- Kajiwara, 2017, An iterative approach for the global estimation of sentence similarity, PloS One, 12, 1, 10.1371/journal.pone.0180885 · DOI
- Lopez-Gazpio, 2017, Interpretable semantic textual similarity: Finding and explaining differences between sentences, Knowledge-Based Systems, 119, 186, 10.1016/j.knosys.2016.12.013 · DOI
- Oliva, 2011, SyMSS: A syntax-based measure for short-text semantic similarity, Data and Knowledge Engineering, 70, 390, 10.1016/j.datak.2011.01.002 · DOI
- Pagliardini, 2017, Unsupervised learning of sentence embeddings using compositional n-gram features, CoRR
- Sahi, 2017, A novel technique for detecting plagiarism in documents exploiting information sources, Cognitive Computation, 9, 852, 10.1007/s12559-017-9502-4 · DOI
- Vani, 2018, Unmasking text plagiarism using syntactic-semantic based natural language processing techniques: Comparisons, analysis and challenges, Information Processing and Management, 54, 408, 10.1016/j.ipm.2018.01.008 · DOI
- Xu, 2014, Extracting lexically divergent paraphrases from Twitter, Transactions of the Association for Computational Linguistics, 2, 435, 10.1162/tacl_a_00194 · DOI
- Yin, 2016, ABCNN: Attention-based convolutional neural network for modeling sentence pairs, Transactions of the Association for Computational Linguistics, 4, 259, 10.1162/tacl_a_00097 · DOI · Paper page
Cited by
Arabic text classification using deep learning models
Elnagar, A., Al-Debsi, R., & Einea, O. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2019.102121 · Cited by 274
Academic Plagiarism Detection: A Systematic Literature Review
Foltýnek, T., Meuschke, N., & Gipp, B. (2020) · ACM Computing Surveys · doi:10.1145/3345317 · Cited by 238
Do Language Models Plagiarize?
Lee, J., Le, T., Chen, J., & Lee, D. (2023) · Proceedings of the ACM Web Conference 2023 · doi:10.1145/3543507.3583199 · Cited by 51
“[2] used Convolutional Neural Network (CNN) to obtain the local region information from n-grams and applied Recurrent Neural Network (RNN) to capture the long-term dependency information.”
MethodDo Language Models Plagiarize?
Lee, J., Le, T., Chen, J., & Lee, D. (2022) · arXiv · doi:10.48550/arxiv.2203.07618 · Cited by 51
Plagiarism types and detection methods: a systematic survey of algorithms in text analysis
Amirzhanov, A., Turan, C., & Makhmutova, A. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1504725 · Cited by 31
Metadata
- Authors
- Agarwal, B., Ramampiaro, H., Langseth, H., & Ruocco, M.
- Venue
- Information Processing & Management
- Publisher
- Elsevier BV
- Published
- 2018-11
- Volume
- 54
- Issue
- 6
- Pages
- 922-937
- ISSN
- 0020-0271 (ISSN-L)
- 0306-4573
- OpenAlex
- W2773143256
- Cited by
- 119
- References
- 6
- FWCI
- 9.19
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.