Improving Vector Space Word Representations Using Multilingual Correlation
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
The distributional hypothesis of Harris (1954), according to which the meaning of words is evidenced by the contexts they occur in, has motivated several effective techniques for obtaining vector space semantic representations of words using unannotated text corpora. This paper argues that lexico-semantic content should additionally be invariant across languages and proposes a simple technique based on canonical correlation analysis (CCA) for incorporating multilingual evidence into vectors generated monolingually. We evaluate the resulting word representations on standard lexical semantic evaluation tasks and show that our method produces substantially better semantic representations than monolingual techniques.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
“Besides, Hewitt and Manning [125], Jawahar et al. [126], Kim et al. [127] proposed several methods to extract dependency trees and constituency trees from BERT, which proved the BERT's ability to encode syntax structure.”
From Pre-trained models for natural language processing: A survey (2020) · cites this paper as [125]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 6×
“This dataset contains word pairs that are different syntactic forms of a given word and was prepared by Mikolov et al. (2013a).”
BackgroundMethodInfluentialIndexing by latent semantic analysis
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., & Harshman, R. (1990) · Journal of the American Society for Information Science · doi:10.1002/(sici)1097-4571(199009)41:6<391::aid-asi1>3.0.co;2-9 · Cited by 12,751
Golub, G. H., & Loan, C. F. V. (1996) · Johns Hopkins University Press eBooks · Cited by 6,027
A unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058 · cited 6×
“Our method can also be seen as an application of multi-view learning (Chang et al., 2013; Collobert and Weston, 2008), where one of the views can be used to capture cross-lingual information.”
BackgroundMethodInfluentialHarris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms
Dietterich, T. G. (1998) · Neural Computation · doi:10.1162/089976698300017197 · Cited by 3,840 · cited 2×
“01) according to the McNemar’s test (Dietterich, 1998).”
MethodInfluentialWord association norms, mutual information, and lexicography
Church, K., & Hanks, P. (1990) · doi:10.5555/89086.89095 · Cited by 3,590
Linguistic Regularities in Continuous Space Word Representations
Mikolov, T., Yih, W.-T., & Zweig, G. (2013) · North American Chapter of the Association for Computational Linguistics · Cited by 2,912
From Frequency to Meaning: Vector Space Models of Semantics
Turney, P. D., & Pantel, P. (2010) · Journal of Artificial Intelligence Research · doi:10.1613/jair.2934 · Cited by 2,866 · cited 1×
“Using cooccurrence statistics from a large corpus of text (Deerwester et al., 1990; Turney and Pantel, 2010), 1 it is possible to construct high-quality semantic vectors — as judged by both correlations with human judgements of semantic relatedness (Turney, 2006; Agirre et al., 2009) and as…”
Background
Cited by
Items 401–500 of 617
Constrained Non-Affine Alignment of Embeddings
Wang, Y., Zheng, Y., Peng, Y., Yeh, M., Zhuang, Z., Mahashweta, D., Bendre, M., Li, F., Zhang, W., & Phillips, J. M. (2021) · Proceedings · doi:10.1109/icdm51629.2021.00179 · Cited by 3
Investigating Cross-Lingual Transfer Learning Techniques for Urdu Text Using Word Embeddings
Rehman, S. U., Tahir, B., & Mehmood, M. A. (2021) · International Conference on Open Source Systems and Technologies (ICOSST) · doi:10.1109/icosst53930.2021.9683873 · Cited by 3
Crosslingual Section Title Alignment in Wikipedia
Difallah, D. E., Sáez-Trumper, D., Augustine, E., West, R., & Zia, L. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020462 · Cited by 3
Cross-lingual embedding methods and applications: A systematic review for low-resourced scenarios
Sindane, T., Marivate, V. N., & Modupe, A. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100157 · Cited by 8
Cross-modal attribute recognition in fashion
Zoghbi, S., Heyman, G., Gómez, J. C., & Moens, M. (2015) · Lirias · Cited by 3
Grounding the Lexical Sets of Causative-Inchoative Verbs with Word Embedding
Ponti, E. M., Ježek, E., & Magnini, B. (2016) · Accademia University Press eBooks · doi:10.4000/books.aaccademia.1833 · Cited by 3
Cross-Lingual and Low-Resource Sentiment Analysis
Farra, N. (2019) · doi:10.7916/d8-x3b7-1r92 · Cited by 7
“In this approach, monolingual word vectors are induced separately in each language and a linear or non-linear projection is learned to map the vectors into the same space (Faruqui and Dyer, 2014; Ammar et al., 2016).”
BackgroundArtificial Intelligence and Language
Asher, N. M., & Zweigenbaum, P. (2020) · Springer eBooks · doi:10.1007/978-3-030-06170-8_4 · Cited by 3
Cross-Lingual Transfer Learning for Medical Named Entity Recognition
Ding, P., Wang, L., Liang, Y., Lu, W., Li, L., Wang, C., Tang, B., & Yan, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59410-7_28 · Cited by 5
Koehn, P. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108608480.009 · Cited by 7
On Support Recovery With Sparse CCA: Information Theoretic and Computational Limits
Laha, N., & Mukherjee, R. (2022) · IEEE Transactions on Information Theory · doi:10.1109/tit.2022.3214201 · Cited by 3
“, 2009), organizational research (Bagozzi, 2011), natural language processing (Dhillon et al., 2011; Faruqui and Dyer, 2014), fMRI data analysis data analysis”
BackgroundMethodNetwork embeddings from distributional thesauri for improving static word representations
Jana, A., Haldar, S., & Goyal, P. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115868 · Cited by 3
Word Translation using Cross-Lingual Word Embedding: Case of Sanskrit to Hindi Translation
Kumar, R., & Sahula, V. (2022) · International Conference on Artificial Intelligence and Signal Processing (AISP) · doi:10.1109/aisp53593.2022.9760564 · Cited by 3
From unified phrase representation to bilingual phrase alignment in an unsupervised manner
Liu, J., Morin, E., Saldarriaga, S. P., & Lark, J. (2022) · Natural Language Engineering · doi:10.1017/s1351324922000328 · Cited by 4
Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings
Wen-Yi, A. W., & Mimno, D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.71 · Cited by 27
“CLWE approaches involve some levels of supervised alignment (Faruqui and Dyer, 2014; Zou et al., 2013), seed dictionaries (Artetxe et al., 2017; Gouws and Søgaard, 2015) or adversarial training (Lample et al., 2018; Artetxe et al., 2018; Zhang et al., 2017; Miceli Barone, 2016).”
BackgroundSeNSe: embedding alignment via semantic anchors selection
Malandri, L., Mercorio, F., Mezzanzanica, M., & Pallucchini, F. (2024) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00522-z · Cited by 6
Joint Prediction of Word Alignment with Alignment Types
Bigvand, A. M., Bu, T., & Sarkar, A. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00076 · Cited by 4
“Aligments also form the basis for learning multi-lingual word embeddings (Faruqui and Dyer, 2014; Lu et al., 2015) and in the projection of syntactic and semantic annotations from one language to another (Hwa et al.”
Towards 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
Low-Resource Text Classification Using Domain-Adversarial Learning
Grießhaber, D., Vu, N. T., & Maucher, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00810-9_12 · Cited by 3
UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database
Xu, C., Ge, T., Li, C., & Wei, F. (2020) · Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP) · doi:10.18653/v1/2020.aacl-main.24 · Cited by 5
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora
Laville, M., Hazem, A., Morin, E., & Langlais, P. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.527 · Cited by 3
“A comparison of the approaches of Mikolov et al. (2013) and Faruqui and Dyer (2014) with the standard bag of words approach was carried out by Jakubina and Langlais (2017).”
MethodMulti-label, Multi-class Classification Using Polylingual Embeddings
Balikas, G., & Amini, M.-R. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-30671-1_59 · Cited by 4
“In the multilingual setting, [3] proposed an approach to learn bilingual embeddings exploiting parallel and non-parallel text in the languages, [1] proposed to use correlated components analysis, together with small bi-lingual lexicons, to learn how to project embeddings in two separate languages into a common represe…”
BackgroundA Language-Independent Ontology Construction Method Using Tagged Images in Folksonomy
Hamano, S., Ogawa, T., & Haseyama, M. (2017) · IEEE Access · doi:10.1109/access.2017.2786218 · Cited by 3
“CCA is a technique that explores correlations between two sets of features, and it has been reported to be effective for multilingual concept representation [42].”
BackgroundMethodBest Practices for Learning Domain-Specific Cross-Lingual Embeddings
Shakurova, L., Nyari, B., Li, C., & Rotaru, M. (2019) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w19-4327 · Cited by 5
“For instance, (Faruqui and Dyer, 2014) select the target word to which the source word is most frequently aligned in parallel corpora.”
BackgroundTowards a Universal Semantic Dictionary
Castro-Bleda, M. J., Iklódi, E., Recski, G., & Borbély, G. (2019) · Applied Sciences · doi:10.3390/app9194060 · Cited by 3
“74 Faruqui and Dyer [2] proposed a procedure to obtain multilingual word embeddings by 75 concatenating the two word vectors coming from the two languages, applying Canonical Correlation 76 Analysis.”
MethodResultInfluentialYu, P., May, J., & Ji, H. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.57 · Cited by 6
“Early work on multilingual representations learns aligned word or sentence embeddings from dictionaries (Mikolov et al., 2013; Faruqui and Dyer, 2014; Pan et al., 2019), parallel corpora (Gouws et al., 2015; Luong et al., 2015) or semi-supervised or unsupervised approaches (Artetxe et al., 2017;…”
BackgroundCalculation of Chinese-Thai Cross-Language Similarity Based on Sentence Embedding
Yinhan, F., Gang, Z., Weixiu, M., Shunbao, L., Yu, S., & Zhang, K. (2020) · International Conference on Smart Grid and Electrical Automation (ICSGEA) · doi:10.1109/icsgea51094.2020.00064 · Cited by 3
Zhi, W., & Zhang, Y. (2021) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/ickg52313.2021.00046 · Cited by 3
Neural Task Representations as Weak Supervision for Model Agnostic Cross-Lingual TransferPreprint
Jauhar, S. K., Gamon, M., & Pantel, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.01115 · Cited by 3
“Previous solutions include modeling with canonical correlation analysis (Faruqui and Dyer 2014), matrix factorization (Shi et al. 2015) and neural networks (Klementiev, Titov, and Bhattarai 2012).”
MethodA Stronger Baseline for Multilingual Word Embeddings
Dufter, P., & Schütze, H. (2018) · Open access LMU (Ludwid Maxmilian's Universitat Munchen) · doi:10.5282/ubm/epub.61864 · Cited by 3
Esuli, A., Moreo, A., & Sebastiani, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.11459 · Cited by 3
“rning approaches typically require the availability of external parallel corpora [18, 23], bi-lingual lexicons , Vol. 1, No. 1, Article 1. Publication date: January 2016. 1:4 Esuli, Moreo, Sebastiani [12], or machine translation tools [1]. Recently, Conneau et al. [7] proposed a method to align monolingual word embedd…”
MethodMeemi: Finding the Middle Ground in Cross-lingual Word EmbeddingsPreprint
Doval, Y., Camacho-Collados, J., Espinosa-Anke, L., & Schockaert, S. (2019) · arXiv (Cornell University) · Cited by 3
Discovering Bilingual Lexicons in Polyglot Word EmbeddingsPreprint
KhudaBukhsh, A. R., Palakodety, S., & Mitchell, T. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.13347 · Cited by 3
“Bilingual lexicon induction has a rich line of prior literature [18, 19, 20, 21, 22, 23, 24, 25] with modern methods [4, 26, 27, 6, 28, 29, 30, 31, 2, 3, 11, 32, 33] leveraging continuous representation of words [9, 34, 35].”
"Wikily" Neural Machine Translation Tailored to Cross-Lingual Tasks.Preprint
Rasooli, M. S., Callison-Burch, C., & Wijaya, D. T. (2021) · arXiv (Cornell University) · Cited by 3
Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces
Prokhorov, V., Pilehvar, M. T., Kartsaklis, D., Lió, P., & Collier, N. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016900 · Cited by 6
Temporal Extraction and Retrieval
Alonso, O., & Spaniol, M. (2024) · ACM eBooks · doi:10.1145/3674127.3674137 · Cited by 2
Tonellotto, N. (2024) · ACM eBooks · doi:10.1145/3674127.3674130 · Cited by 5
Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models With Bias Corpus
Jang, T., Jung, H., & Wang, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00188 · Cited by 8
“[55] suggested Centered Kernel Alignment (CKA) as the similarity measure noting its invariance to orthogonal transformation and isotropic scaling, which does not affect dynamic of gradient-based training, unlike CCA variants [34, 72].”
Improved Vector Space Model TF/IDF Using Lexical Relations
Huynh, M. C., & Duong, T. H. (2015) · Cited by 2
Typicality-Based Across-Time Mapping of Entity Sets in Document Archives
Duan, Y., Jatowt, A., Bhowmick, S. S., & Yoshikawa, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18576-3_21 · Cited by 2
“Faruqui et al. obtained bi-lingual word vectors using CCA [9].”
Fast and Accurate Bilingual Lexicon Induction via Matching Optimization
Chi, Z., Huang, H., Zhao, S., Xu, H.-D., & Mao, X.-L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32233-5_57 · Cited by 2
“Following works [9, 13, 23, 2] adopt similar idea but they additionally apply a canonical correlation analysis or add an orthogonality constraint to the mapping matrix, which gain a performance improvement.”
MethodEfficient bilingual lexicon extraction from comparable corpora based on formal concepts analysis
Chebel, M., Latiri, C., & Gaussier, É. (2021) · Natural Language Engineering · doi:10.1017/s135132492100022x · Cited by 2
“Canonical correlation analysis was then used in Faruqui and Dyer (2014) to project the embeddings to a shared space in both languages on the basis of an existing bilingual dictionary.”
MethodEkštein, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-26061-3 · Cited by 2
Unsupervised Alignment of Distributional Word Embeddings
Diallo, A., & Fürnkranz, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-15791-2_7 · Cited by 2
Verberne, S. (2024) · ACM eBooks · doi:10.1145/3674127.3674141 · Cited by 5
Ferro, N., & Maistro, M. (2024) · ACM eBooks · doi:10.1145/3674127.3674132 · Cited by 5
Privacy in Information Retrieval
Soboroff, I. M. (2024) · ACM eBooks · doi:10.1145/3674127.3674139 · Cited by 2
Multilingual visual sentiment concept clustering and analysis
Pappas, N., Реди, М., Topkara, M., Liu, H., Jou, B., Chen, T., & Chang, S. (2017) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-017-0120-4 · Cited by 2
“These language-specific representations have emerged from monolingual corpora using a skip-gram model (from word2vec toolkit), and have been aligned based on bilingual dictionaries into a single shared embedding space using CCA [17], noted as aligned.”
MethodInfluentialInjecting Word Embeddings with Another Language’s Resource : An Application of Bilingual Embeddings
Pandey, P., Pudi, V., & Shrivastava, M. (2017) · International Joint Conference on Natural Language Processing · Cited by 2
On the Reproducibility and Generalisation of the Linear Transformation of Word Embeddings
Yang, X., Ounis, I., McCreadie, R., Macdonald, C., & Fang, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-76941-7_20 · Cited by 2
“Furthermore, recent enhancements have been proposed to make linear transformation more effective, namely: by retrieving translation pairs [5]; or learning a linear transformation matrix based on orthogonal transformation (e.g. by leveraging canonical correlation analysis (CCA) [6, 7] or singular value decomposition (S…”
MethodSkansi, S. (2018) · Undergraduate topics in computer science · doi:10.1007/978-3-319-73004-2_9 · Cited by 2
Connecting Language and Vision to Actions
Anderson, P., Das, A., & Wu, Q. (2018) · doi:10.18653/v1/p18-5004 · Cited by 2
WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking
Rahimi, A., Baldwin, T., & Verspoor, K. M. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.523 · Cited by 5
Non-Linearity in Mapping Based Cross-Lingual Word Embeddings
Zhao, J., & Gilman, A. (2020) · Language Resources and Evaluation · Cited by 3
Embedding Space Correlation as a Measure of Domain Similarity
Beyer, A., Kauermann, G., & Schütze, H. (2020) · Language Resources and Evaluation · Cited by 3
Leon, F. A. L. D., Guéniat, F., & Madabushi, H. T. (2020) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2020.semeval-1.117 · Cited by 8
“Bilingual Canonical Correlation Analysis (BiCCA) was also developed, it is a technique in which monolingual embeddings are mapped to the same space by use of CCA, (M.Faruqui and C.Dyer, 2014).”
MethodExploiting Comparable Corpora to Enhance Bilingual Lexicon Induction from Monolingual Corpora
Nopember, I. T. S., Sholikah, R. W., Morimoto, Y., Arifin, A. Z., Nopember, I. T. S., Fatichah, C., Nopember, I. T. S., Purwarianti, A., & Bandung, I. T. (2020) · International journal of intelligent engineering and systems · doi:10.22266/ijies2020.1031.34 · Cited by 2
“In general, methods of acquiring bilingual lexicons can be divided into two categories: those based on online learning [11, 12] and those based on offline learning [13, 14].”
MethodDistributed Representations of Lexical Sets and Prototypes in Causal Alternation Verbs
Ponti, E. M., Magnini, B., & Ježek, E. (2017) · Italian Journal of Computational Linguistics · doi:10.4000/ijcol.424 · Cited by 2
A Systematic Investigation of KB-Text Embedding Alignment at Scale
Pahuja, V., Gu, Y., Chen, W., Bahrami, M., Liu, L., Chen, W., & Su, Y. (2021) · doi:10.18653/v1/2021.acl-long.139 · Cited by 3
“(b) Alignment using Projection: Inspired by the multilingual word embedding approaches (Mikolov et al., 2013a; Faruqui and Dyer, 2014) which use a linear transformation to map word embeddings from one space to another, we use an affine transformation from the skip-gram vector space to the TransE…”
TaxoTrans: Taxonomy-Guided Entity Translation
Li, Z., Wang, Y., Xiao, Y., Meng, W., Li, Y., & Yang, J. (2022) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3534678.3539188 · Cited by 2
“The most widely adopted approach is to align the pre-trained monolingual word embeddings in different language in the shared space, based on the bilingual supervision such as dictionaries or parallel corpora [3, 17, 38, 48].”
BackgroundMonti, J., Sangati, F., Chiusaroli, F., Benjamin, M., & Sina Mansour, L. (2016) · Accademia University Press eBooks · doi:10.4000/books.aaccademia.1811 · Cited by 12
Polish Corpus of Annotated Descriptions of Images
Wróblewska, A. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/39sjov6tnwtn · Cited by 2
“However, in the age of intensive research on multilingual NLP, e.g. Faruqui and Dyer (2014), it seems to make sense to build even small but high-quality evaluation resources.”
BackgroundAnalyzing Bayesian Crosslingual Transfer in Topic Models
Hao, S., & Paul, M. J. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1158 · Cited by 2
“A popular approach to representation learning comes from the word embedding community, in which words are represented as vectors in an embedding space shared by multiple languages (Ruder et al., 2018; Faruqui and Dyer, 2014; Klementiev et al., 2012).”
BackgroundA Simple Approach to Learning Unsupervised Multilingual Embeddings
Jawanpuria, P., Meghwanshi, M., & Mishra, B. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.240 · Cited by 3
Generation of Word Vectors for Unknown Words without Additional Corpus
Takama, Y., Mori, Y., & Shibata, H. (2020) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wiiat50758.2020.00057 · Cited by 2
“Faruqui et al. proposed generating word vectors, focusing on synonymous relations [5].”
BackgroundKoehn, P. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108608480.008 · Cited by 2
Multilingual Word Embeddings using MultigraphsPreprint
Soricut, R., & Ding, N. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.04732 · Cited by 4
“We use here a similar objective function to the one used by the SkipGram model: argmax v ∑ w ∑ (w,c)∈Gw d log σ(vw · vc) + ∑ (w,c)∈Gw d log σ(−vw · vc) (1) where σ(x) = 11+ex .”
Extending and Improving Wordnet via Unsupervised Word EmbeddingsPreprint
Khodak, M., Risteski, A., Fellbaum, C., & Arora, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.00217 · Cited by 6
Sparse Models of Natural Language Text
Yogatama, D. (2025) · Figshare · doi:10.1184/r1/28840505 · Cited by 3
Density Matching for Bilingual Word EmbeddingPreprint
Zhou, C., Ma, X., Wang, D., & Neubig, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.02343 · Cited by 2
“Early work focused on supervised methods maximizes the similarity of the embeddings of words that exist in a manually-created dictionary, according to some similarity metric (Mikolov et al., 2013; Faruqui and Dyer, 2014; Jawanpuria et al., 2018; Joulin et al., 2018).”
BackgroundTowards a continuous modeling of natural language domainsPreprint
Ruder, S., Ghaffari, P., & Breslin, J. G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09158 · Cited by 2
“In computer vision, methods such as Subspace Alignment (Fernando et al., 2013) or the Geodesic Flow Kernel (Gong et al., 2012) have been used to find such transformations A and B. Similarly, in natural language processing, CCA (Faruqui and Dyer, 2014) and Procrustes analysis (Mogadala and Rettinger, 2016) have been us…”
MethodEmbedding Learning Through Multilingual Concept InductionPreprint
Dufter, P., Zhao, M., Schmitt, M., Fraser, A., & Schütze, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.06807 · Cited by 2
Multilingual Embeddings Jointly Induced from Contexts and Concepts: Simple, Strong and ScalablePreprint
Dufter, P., Zhao, M., & Schütze, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00586 · Cited by 3
“Zou et al. (2013), Xiao and Guo (2014) and Faruqui and Dyer (2014) use similar approaches (e.g., by computing the transformation using CCA).”
BackgroundBilingual Language Modeling, A transfer learning technique for Roman UrduPreprint
Khalid, U., Beg, M. O., & Arshad, M. U. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.10958 · Cited by 3
“Another line of work focuses on utilising the isomorphic structure of languages, dictionary mappings and shared vocabulary for ad-hoc mappings between languages (Artetxe et al., 2018; Faruqui and Dyer, 2014).”
BackgroundGlobalTrait: Personality Alignment of Multilingual Word Embeddings
Siddique, F. B., Bertero, D., & Fung, P. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017015 · Cited by 1
Meemi: A simple method for post-processing and integrating cross-lingual word embeddings
Doval, Y., Camacho-Collados, J., Espinosa-Anke, L., & Schockaert, S. (2021) · Natural Language Engineering · doi:10.1017/s1351324921000280 · Cited by 9
“Another approach was taken by Faruqui and Dyer (2014), who proposed to learn linear transformations W s and W t , which respectively map vectors from the source and target language word embeddings onto a shared vector space.”
BackgroundMethodInfluentialWord Embedding Interpretation using Co-Clustering
Albujasim, Z. M., Inkpen, D. Z., & Guo, Y. (2022) · doi:10.5121/csit.2022.122210 · Cited by 1
“We use the standard word similarity benchmarks described in [15].”
MethodeCommerce Search and Discovery
Kallumadi, S. T., & King, T. H. (2024) · ACM eBooks · doi:10.1145/3674127.3674140 · Cited by 1
Bilingual Lexicon Extraction with Forced Correlation from Comparable Corpora
Zhang, C., & Zhao, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26535-3_60 · Cited by 1
Zhang, C., & Zhao, T. (2016) · Communications in computer and information science · doi:10.1007/978-981-10-3635-4_3 · Cited by 1
Extending Monolingual Semantic Textual Similarity Task to Multiple Cross-lingual Settings
Hayashi, Y., & Luo, W. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/46ypz239c4gg · Cited by 1
“…both employing distributional/distributed representation could be possible: (1) first map the words in the target sentences into a common space (Faruqui et al., 2014), and then compare the semantic sentence vectors, which would be compositionally composed (Mitchell and Lapata, 2008); (2)…”
BackgroundMarie, B., & Fujita, A. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00075 · Cited by 1
Reranking Candidate Lists for Improved Lexical Induction
Jakubina, L., & Langlais, P. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-89656-4_10 · Cited by 1
“3 Canonical Correlation Analysis (Faru) In [22], the authors propose a technique based on canonical correlation analysis which transforms two existing monolingual embeddings so as to maximize the correlation between representations of words paired in a bilingual lexicon.”
BackgroundMethodEnglish-Chinese Cross Language Word Embedding Similarity Calculation
Wang, L., Sun, Y., & Zhao, X. (2018) · Artificial Intelligence and Cloud Computing Conference (AICCC) · doi:10.1145/3299819.3299831 · Cited by 1
“Orthogonal transformations are more robust to noise, enabling us to learn the transformation without expert bilingual signal by constructing a pseudo-dictionary from the identical character strings which appear in both languages [21].”
BackgroundMethodExploring the Value of Multi-View Learning for Session-Aware Query Representation
Ortiz, D., Moreno, J. G., Hubert, G., Pinel-Sauvagnat, K., & Tamine, L. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.23 · Cited by 4
Hwang, D. Y., Taha, B., & Nechaev, Y. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.625 · Cited by 1
“Word Similarity : We consider diverse databases of word pairs with similarity scores rated manually by humans from Faruqui and Dyer (2014).”
MethodAgrawal, A., Singh, L., Jacobs, E., Liu, Y., Dunlevy, G., Pokharel, R., & Uppala, V. (2023) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa60987.2023.10302481 · Cited by 4
English-Manipuri Cross-Lingual Embedding: A Preliminary Study
Naorem, D., Singh, O. J., Singh, S. R., & Sarmah, P. (2023) · International Conference on Asian Language Processing · doi:10.1109/ialp61005.2023.10337115 · Cited by 2
Embarking on a Preliminary Exploration: Cross-Lingual Embedding in English-Manipuri
Naorem, D., Singh, S. R., & Sarmah, P. (2024) · International Journal of Asian Language Processing · doi:10.1142/s2717554524500073 · Cited by 2
Cross-Lingual Word Embedding Generation Based on Procrustes-Hungarian Linear Projection
Xing, H., Wu, N., Ji, Y., Liu, Y., Liu, N., & Lu, M. (2024) · International Conference on Asian Language Processing · doi:10.1109/ialp63756.2024.10661153 · Cited by 2
“Canonical Correlation Analysis (CCA) methods involve independent transformation matrices for each language, aiming to maximize the correlation between the vectors in the transformation matrices to learn cross-lingual word embeddings [2].”
MethodGaluščáková, P., Oard, D. W., & Nair, S. (2024) · ACM eBooks · doi:10.1145/3674127.3674136 · Cited by 3
Gómez, E., Cuesta, H., Gkiokas, A., Gómez-Cañón, J. S., Porcaro, L., & Yesiler, F. (2024) · ACM eBooks · doi:10.1145/3674127.3702959 · Cited by 5
Baeza-Yates, R. A., Murgai, L., & Dudy, S. (2024) · ACM eBooks · doi:10.1145/3674127.3674138 · Cited by 1
Deep Multi-cultural Graph Representation Learning
Sharifirad, S., & Matwin, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-57351-9_46 · Cited by 1
Word and Phrase Dictionaries Generated with Multiple Translation Paths
Vankka, J., Aminoff, C., Haralson, D., & Siipola, J. (2018) · Communications in computer and information science · doi:10.1007/978-3-319-99972-2_42 · Cited by 1
Vargas, F., Brestnichki, K., Korfiatis, A. P., & Hammerla, N. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1170 · Cited by 1
“We further demonstrate the quality of our multi-lingual word embeddings on monolingual word- and sentence-level similarity tasks from (Faruqui and Dyer, 2014b), which we believe provides empirical evidence that the aligned embeddings preserve and even potentially enhance their monolingual quality.”
BackgroundMethodInfluentialLearning Unsupervised Word Mapping via Maximum Mean Discrepancy
Yang, P., Luo, F., Wu, S., Xu, J., & Zhang, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32233-5_23 · Cited by 1
Massively Multilingual Sparse Word Representations
Berend, G. (2020) · SZTE Publicatio Repozitórium (University of Szeged) · Cited by 1
Unsupervised Cross-Lingual Word Embeddings Learning with Adversarial Training
Li, Y., Zhang, Y., Li, P., & Hu, X. (2019) · IEEE International Conference on Big Knowledge (ICBK) · doi:10.1109/icbk.2019.00029 · Cited by 3
“Faruqui and Dyer [10] employed canonical correlation analysis to transform embeddings of two languages to a shared vector space by two linear transformations.”
MethodBiswas, R., Alam, M., & Sack, H. (2020) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.48550/arxiv.2002.09247 · Cited by 6
“In [10,23,1], the authors have attempted to improve cross lingual word embeddings based on bilingual word lexicons.”
Background
Metadata
- Authors
- Faruqui, M., & Dyer, C.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics
- Published
- 2014
- Pages
- 462-471
- OpenAlex
- W342285082
- Cited by
- 620
- References
- 43
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 33 · 2023: 19 · 2022: 28 · 2021: 57 · 2020: 106 · 2019: 100 · 2018: 91 · 2017: 61 · 2016: 67 · 2015: 33 · 2014: 14
- FWCI
- 34.35
- Type
- conference paper
- Language
- en
- Open access
- green
- figshare.com
- Licence
- cc-by
- Locations
- Conference of the European Chapter of the Association for Computational Linguistics (publishedVersion)
- KiltHub Repository (submittedVersion)
- Figshare (submittedVersion, cc-by)
- KiltHub Repository
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- word embeddings, multilingual word representation, distributional semantics, canonical correlation analysis, word meaning, word sense disambiguation, word similarity
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.