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?
The cited source says what the claim attributes to it.
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 301–341 of 341
Zhang, W., Fan, Q., Liu, X., & Sun, J. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9901629
Inferring Image Background from Text Description
Chizhikov, D., Efimova, V., Shalamov, V., & Filchenkov, A. A. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-23372-2_1
Karlita, T., Afrianto, F., Ramadijanti, N., Basuki, A., Shabrina, U. I., Adiputra, A. A., & Dzalhaqi, M. (2022) · Advances in Social Science, Education and Humanities Research/Advances in social science, education and humanities research · doi:10.2991/978-2-494069-83-1_112
Interactive Context-Comparative Model for Text Matching
Zou, Z., Yang, W., Pang, L., & Chen, L. (2022) · IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC) · doi:10.1109/icftic57696.2022.10075199
“[8] used BiLSTM, average pooling 2022 4th International Conference on Frontiers Technology of Information and Computer (ICFTIC)”
MethodSemantic Matching Research based on Interactive Multi-head Attention Mechanism
Liao, Y.-L., & Li, T. (2022) · International Conference on Telecommunications and Communication Engineering (ICTCE) · doi:10.1145/3577065.3577110
“The twin network structure diagram shown in the above figure 1 Network1 and Network2 are two neural networks, the two neural networks have the same weights, and in the Siamease network structure, the same neural network can be taken for the same neural network or different neural networks [11].”
BackgroundAntonymy-Synonymy Discrimination through Repelling Parasiamese Neural Networks
Etcheverry, M., & Wonsever, D. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191764
“Deep Metric learning has been considered in tasks such as fingerprint and palmprint recognition [21, 22, 23], speaker identification [24] and paraphrase detection [25], among very many others.”
BackgroundKnowledge-aware representation learning for natural language processing applications
Zhang, J. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/171068
Hierarchical and Multiple-Perspective Interaction Network for Long Text Matching
Zou, Z., Huang, Z., Yang, W., Pang, L., Liang, C., & Liu, Q. (2024) · IEEE Access · doi:10.1109/access.2024.3354723
“Neculoiu et al. [35] used Siamese-structured BiLSTM to extract global features of the text, and model the semantics of the text, and subsequently used similarity scores to measure the degree of text matching with good results.”
MethodWho is answering to whom? Modeling reply-to relationships in Russian asynchronous chats
RAS, F. C., Buyanov, I., Yaskova, D., AI, M., Соченков, И. В., & RAS, F. C. (2023) · Computational Linguistics and Intellectual Technologies · doi:10.28995/2075-7182-2023-22-1052-1060
Offline Signature Verification Using Neural Network Technology
Shukla, S., Mittal, A., Rajput, Y. M., Kumbhar, V., & Singh, T. P. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8476-3_28
Liu, H., & Luo, X. (2023) · International Conference on Information Science and Education (ICISE-IE) · doi:10.1109/icise-ie60962.2023.10456509
“One promising avenue involves the exploration of advanced techniques, particularly delving into the realm of deep learning-based models as suggested by recent studies[10].”
BackgroundXu, J., Lei, L., Ma, Z., Tan, Y., Liu, B., & Wang, F. (2023) · International Conference on Smart Power & Internet Energy Systems (SPIES) · doi:10.1109/spies60658.2023.10475076
“Neculoiu [9] built a siamese network composed of bidirectional recurrent neural networks to calculate similarity to achieve text pairing.”
BackgroundDavar, O., & Eftekhari, M. (2024) · CSI International Symposium on Artificial Intelligence and Signal Processing · doi:10.1109/aisp61396.2024.10475270
“In [18], similar to our work, siamese networks were used to measure similarity between words but the input to the network was at the character level, and a Bidirectional LSTM architecture was used in its sub-network for the task job title normalization.”
MethodSingh, A., Kumar, A., & Lukose, S. (2024) · International Conference for Innovation in Technology (INOCON) · doi:10.1109/inocon60754.2024.10512081
“[5] applied SNNs for signature verification.”
280 Characters to Employment: Using Twitter to Quantify Job Vacancies
Sobol, B., Tonneau, M., Fraiberger, S. P., Lee, D., & Grinberg, N. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31403
Digitale Tools für smarte Personalarbeit
Gärtner, C. (2024) · Springer eBooks · doi:10.1007/978-3-658-44904-9_4
Neural Networks Based Fuzzy Join Algorithm In Big Data Processing
Phan, T., Tran, T.-T.-Q., Phan, A.-C., & Trieu, T.-N. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0437-1_13
Perception-Aware Attack Against Music Copyright Detection: Impacts and Defenses
Duan, R., Qu, Z., Zhao, S., Ding, L., Liu, Y., & Lu, Z. (2024) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2024.3522849
“7(1), the SNN consists of two identical subnetworks and takes in two separate inputs, such as two images [78], [79], [80] or text [81], [82], [83] vectors, and can be used to process audio signals [84], [85], [86] as well.”
Context-aware automated ICD coding: A semantic-driven approach
Reshma, O. K., Saleena, N., & Nazeer, K. A. A. (2025) · Information Systems · doi:10.1016/j.is.2025.102539
Improved Text Summarization with RL-Enabled PEGASUS and Siamese Network Evaluation
Dhyuti, N. S., Mercy Faustina, J., & Sivaselvan, B. (2024) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon61640.2024.10902830
“Siamese Networks determine similarity between inputs such as images or text [7].”
Mamba for Scalable and Efficient Personalized Recommendations
Starnes, A., & Webster, C. (2024) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw65004.2024.00018 · Cited by 2
“We use the music recommendation dataset from [6].”
A Deep Learning-Based Framework for the Normalization of WOS Institutional Names
Shi, L., Lu, Y., Zhou, C., Chenxi, W., & Zhou, Y. X. (2025) · International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID) · doi:10.1109/icaid65275.2025.11034643
Romanov, A., Kurtukova, A., Fedotova, A., & Shelupanov, A. A. (2025) · IEEE Access · doi:10.1109/access.2025.3584616 · Cited by 3
“This model is SimNN [37], [38].”
Dynamic Weight Adjustment in Siamese Multi-Head Self-Attention for Text Similarity
He, Z. (2025) · International Symposium on Big Data and Applied Statistics (ISBDAS) · doi:10.1109/isbdas64762.2025.11116855
“Recurrent Neural Networks (RNNs) for Text Similarity: To overcome the limitations of feature-based methods, deep learning models, particularly Recurrent Neural Networks (RNNs) [12], have been introduced to capture the sequential nature of text.”
Research on Text Similarity Algorithm for Fusion of Multiple Features
Li, L., Xiao, S., Zhao, L., Jin, J., & Guo, G. (2025) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac65194.2025.11166428
“Siamese-BiLSTM[21]: Encodes each input sequence using BiLSTM and calculates similarity by concatenating forward and backward hidden states.”
Wang, H., Song, Q., Li, B., & Li, Z. (2025) · Chinese Control Conference (CCC) · doi:10.23919/ccc64809.2025.11178613
Methods and challenges in job recommendation systems: A review
Hasan, M. R., Goh, H.-N., Ting, C., Quek, A., & Haque, R. (2025) · AIP conference proceedings · doi:10.1063/5.0299300
Hitesh, P., Damana, A. A., & Selvakumar, P. (2025) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa65407.2025.11166350 · Cited by 1
“Neculoiu et al. [10] extended this work with character-level embeddings, which proved particularly effective for handling typos and abbreviations common in business documents.”
Using Fuzzy String Comparison for Automated Transfer of Formatting in Poetic Works
Тесля, Н. Н., Беляк, Г. Н., & Teslya, N. N. (2025) · Bulletin of the South Ural State University Series Mathematical Modelling Programming and Computer Software · doi:10.14529/mmp250308
Reference Recommendation for Large Language Models-Generated Text Using Deep Textual Representations
Bashir, S. (2026) · Romanian Journal of Information Science and Technology · doi:10.59277/romjist.2026.1.01
“These networks have proven successful in learning semantic similarity between sentences and paragraphs [27, 29].”
O‘ZBEK TILI MATNLARI SEMANTIK O‘XSHASHLIGINI ANIQ MODELLARINING ILMIY-NAZARIY TAHLILI
Muradovna, A. N. (2026) · Journal of science and innovative development · doi:10.36522/2181-4317/2026-1/34-44
Huang, Z., Han, Q., Guo, L., Zhang, Y., Yu, G., Chong, Z., Li, Z., & Mi, W. (2026) · Discover Computing · doi:10.1007/s10791-026-10043-x
Deep Semantic Matching Based on Selective Feature Attention and Divide-and-Conquer Strategy
Ren, Y., Zhang, C., & Li, B. (2025) · International Conference on Big Data and Data Mining (BDDM) · doi:10.1109/bddm68348.2025.11442131
Appariements collaboratifs des offres et demandes d’emploi
Schmitt, T. (2018) · theses.fr (ABES) · doi:10.70675/d918e2c4za5a2z4d57za561z73d43a7698d5
Cold-start recommendation : from Algorithm Portfolios to Job Applicant Matching
Gonard, F. (2018) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.70675/222c3b16z7046z4cf2za432zc050f4bd04e7
Belkacem, T. (2019) · theses.fr (ABES) · doi:10.70675/f480bd4dz0f08z4e64z9c2fz484276575ac4
Spoken Language Understanding for Abstractive Meeting Summarization
Shang, G. (2021) · theses.fr (ABES) · doi:10.70675/563b2ce0z6d9fz406ezaa17z460d6d1242b0 · Cited by 2
Diffusion-Aware Recommendation in Social Media
Feng, Y. (2023) · theses.fr (ABES) · doi:10.70675/9c8fb2aaz617ez4446z915az003612aa6342
Hierarchy-Aware Heterogeneous Graph Neural Network for Occupation Title Coding
Xie, Y., & Zhu, W. (2026) · Journal of Official Statistics · doi:10.1177/0282423x261436204
“The model combines a stack of character-level bidirectional Long Short-Term Memory (LSTM) with a siamese architecture (Neculoiu et al. 2016).”
GSAG: Global Semantic Fusion with AMR Graphs for Chinese Short Text Matching
Fu, J., & Feng, Y. (2026) · International Conference on Computer, Artificial Intelligence and Control Engineering (CAICE) · doi:10.1145/3804601.3804669
“EarlyRNN-based models (BiLSTM [14]) encode text sequentially but process sentences independently, limiting fine-grained interactions.”
Efficient Backdoor Mitigation in Federated Learning With Contrastive Loss
Ferguson, H. C., Ning, R., Wu, H., Zhu, L., Xin, C., Uddin, M. S., & Li, J. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3711587
“…M c via knowledge distillation from the suspicious global model M s ; 2) initializes a learnable input perturbation and optimizes it while extracting feature vectors from both models; and 3) maximizes the feature discrepancy between M c and M s through a contrastive objective [27], [28], [29].”
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
