The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Learning Text Similarity with Siamese Recurrent Networks
Open accessAbstract
This paper presents a deep architecture for learning a similarity metric on variablelength character sequences.The model combines a stack of character-level bidirectional LSTM's with a Siamese architecture.It learns to project variablelength strings into a fixed-dimensional embedding space by using only information about the similarity between pairs of strings.This model is applied to the task of job title normalization based on a manually annotated taxonomy.A small data set is incrementally expanded and augmented with new sources of variance.The model learns a representation that is selective to differences in the input that reflect semantic differences (e.g., "Java developer" vs. "HR manager") but also invariant to nonsemantic string differences (e.g., "Java developer" vs. "Java programmer").
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Siamese networks are widely applied in nonlinear metric learning across domains such as computer vision and speech recognition.”
From Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches (2025) · cites this paper as [47]
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 · cited 2×
“In this equation and below the logistic function is denoted by σ The Long Short-Term Memory (Hochreiter and Schmidhuber, 1997) variant of RNNs in particular has had success in tasks related to natural language processing, such as text classification (Graves, 2012) and language translation (Sutskever…”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The parameters of the model are optimized using the Adam method (Kingma and Ba, 2014) and each model is trained until convergence.”
MethodGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×
“, 2013) and Glove (Pennington et al., 2014) have seen much use in such models, but some go beyond the word level and represent text as a sequence of characters (Kim et”
Background(2014) · Cited by 33,419
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 2×
“In the last few years, neural network models have been applied to tasks ranging from machine translation (Zou et al., 2013; Cho et al., 2014) to question answering (Weston et al.”
MethodDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 3×
“For example, word similarity models based on dense embeddings (Mikolov et al., 2013) have recently been applied in diverse settings, such as sentiment analysis (dos Santos and Gatti, 2014) and recommender systems (Barkan and Koenig-stein, 2016).”
BackgroundMethodReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“…and below the logistic function is denoted by σ The Long Short-Term Memory (Hochreiter and Schmidhuber, 1997) variant of RNNs in particular has had success in tasks related to natural language processing, such as text classification (Graves, 2012) and language translation (Sutskever et al., 2014).”
BackgroundBidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 1×
“(1) Bidirectional RNNs (Schuster and Paliwal, 1997) incorporate both future and past context by running the reverse of the input through a separate RNN.”
BackgroundNatural Language Processing (almost) from ScratchPreprint
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 6,923 · cited 1×
“The use of (deep) neural networks for NLP has recently received much attention, starting from the seminal papers employing convolutional networks on traditional NLP tasks (Collobert et al., 2011) and the availability of high quality semantic word representations (Mikolov et al., 2013).”
Method
Research works printed but not linked: 5
- Jane Bromley, James W Bentz, Léon Bottou, Is- abelle Guyon, Yann LeCun, Cliff Moore, Eduard Säckinger, and Roopak Shah. 1993. Signature ver- ification using a "siamese" time delay neural net- work. International Journal of Pattern Recognition and Artificial Intelligence, 7(04):669-688.
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013. Distributed representa- tions of words and phrases and their compositional- ity. In Advances in neural information processing systems, pages 3111-3119.
- Mike Schuster and Kuldip K Paliwal. 1997. Bidirec- tional recurrent neural networks. Signal Processing, IEEE Transactions on, 45(11):2673-2681.
- Martijn Spitters, Remko Bonnema, Mihai Rotaru, and Jakub Zavrel. 2010. Bootstrapping information ex- traction mappings by similarity-based reuse of tax- onomies. In CEUR Workshop Proceedings, volume 673.
- Longqi Yang, Yin Cui, Fan Zhang, John P Pollak, Serge Belongie, and Deborah Estrin. 2015. Plate- click: Bootstrapping food preferences through an adaptive visual interface. In Proceedings of the 24th ACM International on Conference on Informa- tion and Knowledge Management, pages 183-192. ACM.
Cited by
Sorted by citations
Items 201–300 of 341
Co-Detection in Images Using Saliency and Siamese Networks
Zinzuvadiya, M., Dhameliya, V., Vaghela, S., Patki, S., Nanavati, N. R., & Bhavsar, A. V. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-981-32-9291-8_28 · Cited by 3
Hybrid Self-Interactive Attentive Siamese Network for Medical Textual Semantic Similarity
An, H., Wu, D. J., & Li, Z. (2020) · International Conference on Management Engineering, Software Engineering and Service Sciences (ICMSS) · doi:10.1145/3380625.3380647 · Cited by 3
“To verify the effectiveness of the proposed method, we reimplement the Siamese Recurrent Neural Network [7] (hereinafter referred to as SRNN, the RNN network in this paper uses Bi-LSTM) as a baseline,this method chooses Google open source.”
MethodJointly Multi-Similarity Loss for Deep Metric Learning
Zhang, L., Shen, S., Li, L., Wang, H., Li, X., & Lang, J. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00190 · Cited by 3
Automatic Scoring Model of Subjective Questions Based Text Similarity Fusion Model
Xie, B., & Chen, L. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-2456-9_60 · Cited by 3
Siamese-Based Architecture for Cross-Lingual Plagiarism Detection in English–Hindi Language Pairs
Agarwal, B., Gupta, M. K., Sharma, H., & Poonia, R. C. (2022) · Big Data · doi:10.1089/big.2020.0243 · Cited by 3
SPM: Structured Pretraining and Matching Architectures for Relevance Modeling in Meituan Search
Zan, W., Han, Y., Jiang, X., Xiao, Y., Yang, Y., Chen, D., & Chen, S. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615500 · Cited by 3
“Neural text matching methods can be categorized into two types: cross-encoder methods [1, 13, 16, 20], and bi-encoder meth-ods [4, 5, 14, 19].”
MethodTowards language-agnostic alignment of product titles and descriptions: a neural approach
Stein, D., Shterionov, D., & Way, A. (2019) · International World Wide Web Conference (WWW) · doi:10.1145/3308560.3316602 · Cited by 3
“It has already been successfully applied for text similarity in [13, 14, 26].”
MethodThe Evaluation of Thai Poem's Content Consistency using Siamese Network
Promrit, N., Waijanya, S., & Thaweesith, K. (2019) · International Conference on Natural Language Processing and Information Retrieval (NLPIR) · doi:10.1145/3342827.3342855 · Cited by 3
“Not only AllenNLP, we found other works related about sentences similarity using Siamese model [4].”
BackgroundVietnamese Sentence Paraphrase Identification using Pre-trained Model and Linguistic Knowledge
Đinh, Đ., & Thanh, N. L. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120891 · Cited by 3
An Semantic Similarity Matching Method for Chinese Medical Question Text
Wang, L., Zhang, T., Tian, J., & Lin, H. (2023) · Communications in computer and information science · doi:10.1007/978-981-19-9865-2_6 · Cited by 3
Learning Contextual Embeddings for Structural Semantic Similarity using Categorical Information
Nicosia, M., & Moschitti, A. (2017) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k17-1027 · Cited by 3
One-Shot Learning on Attributed Sequences
Zhuang, Z., Kong, X., Rundensteiner, E. A., Arora, A., & Zouaoui, J. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622257 · Cited by 4
“Distance metric learning, where the goal is to learn a distance metric from pairs of similar and dissimilar examples, has been extensively studied [13], [32], [33], [34], [35], [36], [11], [37], [38].”
BackgroundPerson Entity Attribute Extraction Based on Siamese Network
Huang, Y., Li, A., Zhou, B., Huang, J., Lan, L., Yin, X., & Jia, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2917302 · Cited by 3
“Besides, Siamese recurrent networks are applied to learn semantic entailment [14], sentence representations [38] and text similarity [39].”
BackgroundA Comparative Study of Ensemble Approaches to Fact-Checking for the FEVER Shared Task
Oni, O. O., & van Zyl, T. L. (2020) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde50874.2020.9411564 · Cited by 3
“When training we intend to minimise the distance between similar pairs and maximise the distance between dissimilar pairs [9].”
BackgroundA Transformer Based Encodings for Detection of Semantically Equivalent Questions in cQA
Kumar, S., & Chauhan, A. (2022) · The Computer Journal · doi:10.1093/comjnl/bxac003 · Cited by 3
Canonicalizing Knowledge Bases for Recruitment Domain
Fatma, N., Choudhary, V., Sachdeva, N., & Rajput, N. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-47436-2_38 · Cited by 3
“In Random selection approach [19] , every variation name e i x is paired with randomly selected variation name e j y from the cluster (i.e. x = y).”
BackgroundCourt Similar Case Recommendation Model Based on Word Embedding and Word Frequency
Yang, F., Chen, J., Huang, Y., & Li, C. (2020) · International Conference on Advanced Computational Intelligence (ICACI) · doi:10.1109/icaci49185.2020.9177720 · Cited by 3
“In recent years, with the extensive application of deep learning, text similarity calculation algorithms via the neural network have been highly developed [1], [2].”
BackgroundDistant supervised relation extraction with label entailment and collaborative denoising
Xie, T., Li, Q. L., Wang, G., & Wang, H. (2025) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-00932-w · Cited by 2
“We adopt the cross-entropy as the classification loss: Toenhancethelearningoftheselectedcleaninstances,weleverageanauxiliarycontrastive loss (Neculoiu et al., 2016) to improve the representation learning.”
An Improved Word Similarity Measure For Ontological Context
Tayal, D. K., Jain, A., Roy, A., & Gupta, M. (2019) · International Conference on Advances in Computing, Communication and Control (ICAC3) · doi:10.1109/icac347590.2019.9036768 · Cited by 2
“And apart from these two, there comes Knowledge based approaches [4] which focus on semantic network [6][8][9]to gain information to compare words For Path based approaches, in taxonomy, distance among the words is used to find out the similarity them.”
BackgroundN2One: Identifying Coreference Object Among User Generated Content with Siamese Network
Yuan, W., Wang, P., Yuan, M., Guo, Y., & He, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60029-7_26 · Cited by 2
Casting the Same Sentiment Classification Problem
Körner, E., Hakimi, A. D., Heyer, G., & Potthast, M. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.53 · Cited by 2
“We then used a Siamese Recurrent Network architecture (Neculoiu et al., 2016; Mueller and Thyagarajan, 2016) that has been successfully applied to semantic textual similarity problems.”
MethodSemantic Preserving Siamese Autoencoder for Binary Quantization of Word Embeddings
Mostard, W., Schomaker, L., & Wiering, M. (2021) · International Conference on Natural Language Processing and Information Retrieval (NLPIR) · doi:10.1145/3508230.3508235 · Cited by 2
“For example [19] applied a bi-directional LSTM with a Siamese architecture for job title normalization and [22] applied it to predict the relatedness of sentence pairs.”
MethodChinese Short Text Matching Model Based on WoBERT Word Embedding Representation and Priori Knowledge
Dong, J. (2023) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece58074.2023.10135350 · Cited by 2
“In 2016, Jonas et al[7] proposed the twin long short-term memory network (Siamese LSTM), where the text is represented by a combination of word vectors and input to the LSTM. Subsequently, Paul et al[8] proposed a twin bi-directional long and short-term memory network (Siamese BiLSTM), which can acquire the informatio…”
BackgroundMethodAutoTag: automated metadata tagging for film post-production
Sandoval-Castañeda, M., Copti, S., & Shasha, D. E. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15565-w · Cited by 2
“Neculoiu, Versteegh, and Rotaru [12] suggest a more modern approach to this problem.”
Integrating Event Elements for Chinese-Vietnamese Cross-Lingual Event Retrieval
Huang, Y., Yuanlin, Y. A. N. G., Zhu, E., Liang, Y., & Xian, Y. (2024) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2024edp7055 · Cited by 2
“Siamese BILSTM: Paul Neculoiu et al.[14] introduced a twin network model based on a bidirectional recurrent neural network specifically designed for calculating the similarity between two input texts.”
BackgroundInterpretable adversarial neural pairwise ranking for academic network embedding
Paul, A., Wu, Z., Chen, B., Luo, K., & Fang, L. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-024-02311-3 · Cited by 2
“This method is widely applied in other fields of research [28–30].”
SynonymNet: Multi-context Bilateral Matching for Entity Synonyms
Zhang, C., Li, Y., Du, N., Fan, W., & Yu, P. S. (2018) · doi:10.13140/rg.2.2.18330.90561 · Cited by 2
Document similarity detection based on multi-feature semantic fusion and concept graph
Xiang, X., Zhong, Z., Chen, Y., & Zhang, Z. (2022) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci55101.2022.9832170 · Cited by 2
Hu, S. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1146 · Cited by 4
“In Section 5, we showcase a modified Siamese Neural Network (Yang et al., 2015; Mueller and Thyagara-jan, 2016; Neculoiu et al., 2016; Pei et al., 2016; Bertinetto et al., 2016) coupled with Bidirectional Long Short-term Memory Networks (Hochreiter and Schmidhuber, 1997; Schuster and Paliwal, 1997;…”
MethodDEM: Deep Entity Matching Across Heterogeneous Information Networks
Kong, C., Chen, B., & Zhang, L. (2020) · Journal of Computer Science and Technology · doi:10.1007/s11390-020-0139-5 · Cited by 2
“Parallelly, Neculoiu et al. presented a different way [37] to learn the contrastive loss from entity embeddings in vector space.”
BackgroundMLAS: Metric Learning on Attributed Sequences
Zhuang, Z., Kong, X., Rundensteiner, E. A., Zouaoui, J., & Arora, A. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378490 · Cited by 2
“Many application domain require distance metric learning, including patient similarity in health informatics [2], face verification in computer vision [4], [5], [9], image recognition [25] and sentence semantic similarity analysis [6], [24].”
BackgroundInfluentialResearch on the Application of BERT in Mongolian-Chinese Neural Machine Translation
Zhi, X., & Wang, S. (2021) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3457682.3457744 · Cited by 2
“• (2) The equivalence/equivalence judgment of sentence pair ( [23, 24] ).”
BackgroundChinese Event Detection Based on Event Ontology and Siamese Network
Ni, C., Liu, W., Li, W., Wu, J., & Ren, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82147-0_36 · Cited by 2
Zhou, L., Zhao, Z., & Dang, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/9948218 · Cited by 2
“LSTM-Siamese [29]: -e model incorporates a character-level bi-directional LSTMs with a Siamese network to match semantics between text pairs.”
MethodSurvey on Decoding Schemes of the Polar Code Using the Deep Learning
Yang, J., & Liu, Y. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-1260-5_19 · Cited by 2
Automatic CWE Assignment for Vulnerabilities with Graph Neural Networks
Liu, P., Ye, W., Duan, H., Li, X., Zhang, S., & Li, Y. (2023) · Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) · doi:10.1109/acctcs58815.2023.00044 · Cited by 2
“Siamese networks is a twin network used for metric learning, i.e., it is composed of two identical sub-networks sharing the same weights[17].”
BackgroundUnlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling
Hartley, Z. K. J., Lind, R. J., Smith, N., Collison, B., & French, A. P. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00075 · Cited by 2
“In the past decade, advances in deep learning have allowed Siamese neural networks to solve a much wider range of problems, including human re-identification [12], COVID-19 diagnosis [10], and text based comparisons as seen in Neculoiu et al [7].”
BackgroundMining Polysemous Triplets with Recurrent Neural Networks for Spoken Language Understanding
Vukotić, V., & Raymond, C. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-2977 · Cited by 2
“Similarly, introducing a triplet loss function was later shown to be successful for computing text similarity [5] with a character-based bidirectional LSTM network, for learning a metric in speaker diarization [6, 7, 8] with an end-to-end to end architecture, and for recognizing speech emotion [9]…”
MethodCanonicalizing Organization Names for Recruitment Domain
Fatma, N., Sachdeva, N., & Rajput, N. (2020) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3371158.3371203 · Cited by 2
“We include the following two methods to generate dissimilar pairs dataset: a) Random selection : First, using the approach given by [15], for every variation name e ix , we randomly select any variation name e jy from the cluster (i.e. x (cid:44) y). b) Lower ranked elements from indexing : We…”
MethodEstimating similarity between differently compiled procedures using neural networks
Pejić, N., Cvetanović, M., & Radivojević, Z. (2019) · Telecommunications Forum (TELFOR) · doi:10.1109/telfor48224.2019.8971103 · Cited by 2
“It represents a Siamese neural network [8] and consists of the following steps: feature extraction – this step takes an assembler file as input and extracts from it a sequence of instruction tokens.”
BackgroundTraceWalk: Semantic-based Process Graph Embedding for Consistency CheckingPreprint
Chen, Q., Wen, L., & Kumar, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.06883 · Cited by 2
“Like [Neculoiu et al., 2016; Mueller and Thyagarajan, 2016], we consider the PCC task as a text similarity evaluation task.”
BackgroundMethodText Similarity Using Siamese Networks and Transformers
Chikoti, B. C. (2022) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2022.44283 · Cited by 1
A Brief Survey of Text Mining: Domains, Implemented Algorithms and Evaluation Metrics
Kavitha, D., & Mala, G. S. A. (2024) · Journal of Information & Knowledge Management · doi:10.1142/s0219649224500783 · Cited by 1
Vaideghy, A., & Thiyagarajan, C. (2024) · International Conference on Science Technology Engineering and Mathematics (ICONSTEM) · doi:10.1109/iconstem60960.2024.10568693 · Cited by 1
“A number of natural language processing (NLP) tasks related to false news detection have demonstrated the effectiveness of deep learning models, such as recurrent neural networks (RNN) and its variations [11], as well as convolutional neural networks (CNN) [12].”
BackgroundImproving cross-lingual representation for semantic retrieval with code-switching
Maimaiti, M., Zheng, Y., Zhang, J., Zhang, Y., Luo, W., & Huang, K. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113919 · Cited by 1
Ahmed, A., Mohandas, R., Joorabchi, A., & Hayes, M. J. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9120312 · Cited by 1
An Approach for Evaluating Semantic Similarity in Research Papers via Siamese BERT Architecture
Sarkar, P., Sarkar, S., Ansar, W., & Chakrabarti, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6537-2_22 · Cited by 1
A deep metric learning algorithm for similarity measure of the gene expression profile
Peng, S., Zhang, L., Yang, Y., Liu, W., Li, F., Hong, H., Li, K., & Wang, S. (2021) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom49281.2021.9398919 · Cited by 1
“The Siamese network[14] is a similarity measurement framework[15, 16], which is designed to deal with the dilemma that lacks samples and used for category identification, classification.”
BiLSTM-Ridge Regression Meta Learning Model for Few-Shot Logs Classification
Shen, H., Li, J., & Fu, X. (2022) · International Conference on Advanced Communication Technology · doi:10.23919/icact53585.2022.9728824 · Cited by 1
“BiLSTM can better understand context and can demonstrate its advantages in many different text mining tasks, such as sentiment analysis [10], sentence similarity [11], and named entity recognition [12] This paper proposed a few-shot Meta learning model based on BiLSTM-Ridge regression.”
MethodSiamese Neural Network and Machine Learning for DGA Classification
Segurola-Gil, L., Egüés, T., Zola, F., & Orduna-Urrutia, R. (2022) · European Conference on Cyber Warfare and Security · doi:10.34190/eccws.21.1.205 · Cited by 1
“(Neculoiu, 2016) is a clear example of this, where a bidirectional LSTM is used to embed the words into a fixed space.”
MethodTextual Plagiarism Detection Using Embedding Models and Siamese LSTM
Saeed, A. A. M., & Taqa, A. Y. (2022) · International Conference for Natural and Applied Sciences (ICNAS) · doi:10.1109/icnas55512.2022.9944717 · Cited by 1
“[17] provided a deep architecture for learning a similarity metric on character sequences of varying length.”
BackgroundZhang, Q., Wang, T., Zhu, M., Shen, T., Zhao, Y., & Zhang, Y. (2022) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea54703.2022.10006207 · Cited by 1
Identifying Meaningful Vulnerability Report in Common Weakness Enumeration
Li, G., We, Z., Zhao, L., Li, H., Guo, S., & Hao, L. (2024) · International Conference on Information Science and Technology · doi:10.1109/icist63249.2024.10805315 · Cited by 1
Improve Word Mover's Distance with Part-of-Speech Tagging
Chen, X., Li, B., Wang, D., & Shi, J. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8546241 · Cited by 1
“Another adaptation [18] of Siamese network is learning a similarity metric, like Manhattan LSTM model but at character level.”
BackgroundZeng, Q., Zhao, H., Duan, H., Li, C., Ni, W., Xie, N., & Diao, X. (2018) · International Conference on Communication and Information Processing (ICCIP) · doi:10.1145/3290420.3290473 · Cited by 1
Nonuniform language in technical writing: Detection and correction
Wang, W., Islam, A., Moh’d, A., Soto, A. J., & Milios, E. (2020) · Natural Language Engineering · doi:10.1017/s1351324920000133 · Cited by 2
“…recent methods based on recurrent neural networks using long short-term memory (LSTM) and word embeddings represent the state of the art in sentence similarity (Neculoiu, Versteegh, and Rotaru 2016), we also integrate a deep siamese LSTM network (Mueller and Thyagarajan 2016) into our NLD method.”
BackgroundMethodImplementasi Library Deep Learning Keras pada Sistem Ujian Essay Online
Ekojono, Rahutomo, F., & Sari, D. N. (2020) · Jurnal Informatika Polinema · doi:10.33795/jip.v6i2.303 · Cited by 1
UNIOR NLP at MWSA Task - GlobaLex 2020: Siamese LSTM with Attention for Word Sense Alignment
Manna, R., Speranza, G., di Buono, M. P., & Monti, J. (2020) · ARCHIVIO ISTITUZIONALE DELLA RICERCA-UNIVERSITA DEGLI STUDI DI NAPOLI "LORIENTALE" · Cited by 1
Digitale Tools für smarte Personalarbeit
Gärtner, C. (2020) · Springer eBooks · doi:10.1007/978-3-658-29431-1_4 · Cited by 1
Learning Neural Textual Representations for Citation Recommendation
Kieu, B. T., Unanue, I. J., Pham, S. B., Phan, H. X., & Piccardi, M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412725 · Cited by 2
“[20], or combined with recurrent neural networks to learn text semantic similarity [21], [22].”
BackgroundSentence Pair Similarity Modeling Based on Weighted Interaction of Multi-semantic Embedding Matrix
Chen, J., Zhu, X., Sang, J., & Gong, L. (2020) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai50040.2020.00170 · Cited by 1
“Siamese network is also a common strategy for sentence matching which passes the two sentences through a neural network with shared parameters and obtains sentence representation in the same embedding space [2,12,25,26].”
BackgroundConverting Image Labels to Meaningful and Information-rich Embeddings
Karatsiolis, S., & Kamilaris, A. (2021) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0010375801070119 · Cited by 1
Detecting Semantically Equivalent Questions Using Transformer-Based Encodings
Bhuse, P., & Bathija, P. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-33-4355-9_5 · Cited by 1
KCNet: Kernel-Based Canonicalization Network for Entities in Recruitment Domain
Goyal, N. P., Sachdeva, N., Goel, A., Kalra, J., & Kumaraguru, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86340-1_13 · Cited by 1
“Similarly, g(ex, e j y) = 0 where x 6= y belongs to different clusters (negative pairs) using a random sampling approach [15].”
MethodREWRITING IDENTIFICATION TECHNOLOGY FOR TEXT CONTENT BASED ON MACHINE LEARNING METHODS
Kholodna, N., & Vysotska, V. (2022) · Radio Electronics Computer Science Control · doi:10.15588/1607-3274-2022-4-11 · Cited by 1
Markchom, T., Liang, H., Gitau, J., Liu, Z., Ojha, V., Taylor, L. R., Bonnici, J., & Alshadadi, A. (2023) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2023.semeval-1.3 · Cited by 1
Siamese Neural Networks for Wireless Positioning and Channel ChartingPreprint
Lei, E., Castañeda, O., Tirkkonen, O., Goldstein, T., & Studer, C. (2019) · arXiv (Cornell University) · doi:10.3929/ethz-b-000448935 · Cited by 1
Multimodal Learning for Non-Small Cell Lung Cancer PrognosisPreprint
Wu, Y., Wang, Y., Huang, X., Yang, F., Wang, H., Sun, W., Ling, S. H., & Su, S. W. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4820740 · Cited by 1
Metric learning for structured data
Pan, J. (2019) · theses.fr (ABES) · doi:10.70675/5c85f85fzb5c8z47c5z8736z2dd52d713193 · Cited by 1
Deep Metric Learning for Sequential Data Using Approximate Information
Thaler, S., Menkovski, V., & Petković, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96136-1_22
Strategies for Language Identification in Code-Mixed Low Resource LanguagesPreprint
Mandal, S., & Sanand, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.07156
“In the recent past, it has become popular for finding textual similarity as well (Mueller and Thyagarajan (2016), Neculoiu et al. (2016), Mou et al. (2016)).”
BackgroundRisk Information Recommendation for Engineering Workers
Martin, K., Liret, A., Wiratunga, N., Owusu, G., & Kern, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04191-5_27
“Due to this they have demonstrated application in areas where fine-grained similarity knowledge is important, such as face verification [15] and similar text retrieval [13].”
BackgroundNIST TAC SM-KBP 2018 System Description: JHU/UR Pipeline
Xia, P., Stengel-Eskin, E., Chen, T., Ebner, S., Holzenberger, N., Culkin, R., Rastogi, P., Ma, X., & Durme, B. V. (2018) · HAL
Neural Rule Grounding for Low-Resource Relation Extraction.Preprint
Zhou, W., Lin, H., Wang, Z., Neves, L., & Ren, X. (2019) · arXiv (Cornell University)
Named entity recognition and linking with knowledge base
Phan, C. M. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/136585 · Cited by 1
Fan, J., Nichols, E., Tompkins, D. G., Méndez, A. E. M., Elizalde, B., & Pasquier, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09026
“images and video [12-15].”
Glazkova, A. V. (2020) · Программные системы и вычислительные методы · doi:10.7256/2454-0714.2020.1.31728
SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence EmbeddingPreprint
Zhang, L., Wang, H., & Li, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11347
“Other works [7, 14, 21] were mostly similar to SentenceBert [24], except that they utilized stacked bi-LSTM or other basic encoder to replace BERT.”
MethodAn Active Learning Framework for Duplicate Detection in SaaS Platforms
Nguyen, Q. H., Nguyen, D., Dao, M.-S., Dang-Nguyen, D.-T., Gurrin, C., & Nguyen, B. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3391933
“Triplet loss has been one of the most well-known loss functions which plays a vital role in many tasks in different applications, including computer vision [16], image retrieval [3, 10], face recognition [12], and sentence matching [6, 7].”
BackgroundThe pursuit of beauty: Converting image labels to meaningful vectorsPreprint
Karatsiolis, S., & Kamilaris, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00665
“on the classification task. Such a classifier compresses the information of an image down to labels and outputs probabilities of label occurrence for an input image. We further use a Siamese network [14, 15, 16, 17] which receives two images and the product of their label probabilities to adapt its output accordingly,…”
MethodLEARNING EMBEDDINGS FOR WEARABLE-BASED HUMAN ACTIVITY ANALYSIS
Sheng, T. (2020)
Evaluation of Siamese Networks for Semantic Code SearchPreprint
Sinha, R., Desai, U., Tamilselvam, S., & Mani, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01043
“, 2015a) and recently in text domain as well (Mueller and Thyagarajan, 2016; Neculoiu et al., 2016; Das et al., 2016).”
BackgroundInfluentialDeep Learning With Sentiment Inference For Discourse-Oriented Opinion Analysis
Marasović, A. (2020) · heiDOK (Heidelberg University) · doi:10.11588/heidok.00027699
Research on anti plagiarism technology for manuscript washing and false original
Liu, J., Xing, L., Zhang, S., & Chang, L. (2020) · International Conference on Culture-oriented Science & Technology (ICCST) · doi:10.1109/iccst50977.2020.00050
“BERT is a pre-trained model, and similarity calculation can be regarded as its downstream task[9].”
BackgroundNeural Network Algorithms for Ontology Informed Information Extraction
Xu, D. (2021) · UA Campus Repository (The University of Arizona)
Deep Learning for Unstructured Data by Leveraging Domain Knowledge
Zhang, S. (2019) · TUScholarShare (Temple University)
NIST TAC SM-KBP 2019 System Description: JHU/UR Framework
Chen, Y., Ebner, S., Chen, T., Xia, P., Stengel-Eskin, E., Su, T.-R., Hu, J., Holzenberger, N., Culkin, R., Harman, C., et al. (2019) · HAL
Jeon, S. H., & Cho, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07549
“Siamese RNN model successfully apprehends the morphological similarity between strings [29].”
BackgroundAn Approach for Buyer Name Normalization in Pharmacy Sales Data
Li, J., Jia, W., Nie, F., You, H., & Hao, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3093028
“For example, Neculoiu et al. [12] present a stack of character-level bidirectional Long Short-Term Memory (LSTM) with a Siamese architecture for job title normalization, and the method well handles typos, near-synonymy, and extra words.”
MethodMatching Document Pairs using Multi-Feature Semantic Fusion Based on Knowledge GraphPreprint
Chen, Y., Zhang, Z., Huang, X., Xiang, X., He, Z., Chen, Y., & Hu, Q. (2021) · Research Square · doi:10.21203/rs.3.rs-907473/v1
“Siam network encoder [41] is applied to each vertex ∈ to transform the word embedding of { , ( )} into a hidden feature vector ( ), which is fixed-sized.”
MethodBarnwal, S. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.11938 · Cited by 5
On Injecting Entropy-Like Features into Deep Neural Networks for Content Relevance Assessment
Sido, J., Ekštein, K., Pražák, O., & Konopík, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90425-8_5
Semantic Matching of Legal Cases for large Scale Judgments of China
Mou, Y., Weng, Y., Gu, S., & Wang, Z. (2021) · International Conference on Computer Science & Education (ICCSE) · doi:10.1109/iccse51940.2021.9569332
Kang, S.-Y., & Mo, J. (2021) · doi:10.2196/preprints.35575
Jurisprudence search based on facts similarity using NLP and ML techniques.
Ruiz, R. A. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.3.2021.tde-14022022-122906
Text Matching application for integration between industry and education
Luo, Y., & Li, X. (2022) · International Conference on Measuring Technology and Mechatronics Automation (ICMTMA) · doi:10.1109/icmtma54903.2022.00145
Identifying environmental homologous complaint reports based on Siamese network
Zhang, W., Fan, Q., Liu, X., & Chen, G. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9727301
Identification of Rail Surface Defects Based on One-Shot Learning
Ji, A., Quek, Y. T., Wong, E. W. L., & Woo, W. L. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-2259-6_73
Ke, X., Zhang, S., & Hu, P. F. (2022) · International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) · doi:10.1109/icmsp55950.2022.9859015
“Thalictrum A [4] proposed a LSTM-based twin network to calculate sentence similarity, used LSTM neural network to extract the latent semantic information of sentences, and used Manhattan distance to calculate the similarity between sentence pairs; Paul [5] used a bidirectional LSTM network as the shared network layer…”
MethodChinese Electronic Medical Record Retrieval Method Using Fine-Tuned RoBERTa and Hybrid Features
Yu, Y., Li, J., Zhu, Z., Pei, Y., Cheng, Z., Zeng, K., & Zhang, F. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-4132-0_7
Metadata
- Authors
- Neculoiu, P., Versteegh, M., & Rotaru, M.
- ORCID
- Versteegh, Maarten
- Venue
- Proceedings of the 1st Workshop on Representation Learning for NLP
- Published
- 2016
- Pages
- 148-157
- OpenAlex
- W2510940142
- Cited by
- 341
- References
- 51
- Citations by year
- 2026: 6 · 2025: 21 · 2024: 30 · 2023: 31 · 2022: 43 · 2021: 63 · 2020: 64 · 2019: 37 · 2018: 36 · 2017: 9
- FWCI
- 14.73
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Workshop on Representation Learning for NLP (RepL4NLP) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Data Quality and Management
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Keywords
- text similarity, Siamese network, bidirectional LSTM, character embeddings, similarity metric learning, taxonomy (general classification scheme), data augmentation, semantic representation, string embeddings
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
