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
Pre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591
“tions shared across languages plays an important role in many cross-lingual NLP tasks. Cross-Lingual Language Understanding (XLU) Most of the early works focus on learning multilingual word embedding [45, 123, 158], which represents text from multiple languages in a single semantic space. However, these methods usuall…”
BackgroundCross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586
“A series of follow-up studies show that cross-lingual representations can be used to improve the quality of monolingual representations [16], that orthogonal transformations are sufficient to align these word distributions [43], and that all these techniques can be applied to an arbitrary number of languages [2].”
BackgroundWord Translation Without Parallel Data
Conneau, A., Lample, G., Ranzato, M., Denoyer, L., & Jeǵou, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.04087 · Cited by 219
“Since then, several works aimed at improving these cross-lingual word embeddings (Faruqui & Dyer (2014); Xing et al. (2015); Baroni et al. (2015); Ammar et al. (2016); Artetxe et al. (2016); Smith et al. (2017)), but they all rely on bilingual word lexicons.”
BackgroundOn Deep Multi-View Representation Learning
Wang, W., Livescu, K., & Bilmes, J. (2015) · Cited by 871
Retrofitting Word Vectors to Semantic Lexicons
Faruqui, M., Dodge, J., Jauhar, S. K., Dyer, C., Hovy, E., & Smith, N. A. (2015) · Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.3115/v1/n15-1184 · Cited by 721
Self-citationVisualizing and Understanding Neural Models in NLP
Li, J., Chen, X., Hovy, E., & Jurafsky, D. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1082 · Cited by 625
“Similarity is commonly visualized graphically, generally by projecting the embedding space into two dimensions and observing that similar words tend to be clustered together (e.g., Elman (1989), Ji and Eisenstein (2014), Faruqui and Dyer (2014)).”
BackgroundMultilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
Chen, M., Tian, Y., Yang, M., & Zaniolo, C. (2017) · Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/209 · Cited by 531
“For the baselines, LM and CCA are again left far behind for being disjointedly trained.”
BackgroundInfluentialA robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
Artetxe, M., Labaka, G., & Agirre, E. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1073 · Cited by 751
“, 2015), canonical methods, which map the embeddings in both languages to a shared space using canonical correlation analysis and extensions of it (Faruqui and Dyer, 2014; Lu et al., 2015), orthogonal methods, which map the embeddings in one or both languages under the constraint of the transformation being orthogonal…”
BackgroundA Survey of Cross-lingual Word Embedding Models
Ruder, S., Vulić, I., & Søgaard, A. (2018) · Apollo (University of Cambridge) · doi:10.17863/cam.30462 · Cited by 510
Learning bilingual word embeddings with (almost) no bilingual data
Artetxe, M., Labaka, G., & Agirre, E. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1042 · Cited by 455
“Instead of learning a single linear transformation from the source language into the target language, Faruqui and Dyer (2014) use canonical correlation analysis to map both languages to a shared vector space.”
BackgroundXNLI: Evaluating Cross-lingual Sentence Representations
Conneau, A., Lample, G., Rinott, R., Williams, A., Bowman, S. R., Schwenk, H., & Stoyanov, V. (2018) · arXiv · doi:10.48550/arxiv.1809.05053 · Cited by 399
Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation
Xing, C., Wang, D., Liu, C., & Lin, Y. (2015) · Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.3115/v1/n15-1104 · Cited by 381
“More importantly, the embedding encodes syntactic and semantic content implicitly, so that relations among words can be simply computed as the distances among their embeddings, or word vectors.”
BackgroundTwo/Too Simple Adaptations of Word2Vec for Syntax Problems
Ling, W., Dyer, C., Black, A. W., & Trancoso, I. (2015) · Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.3115/v1/n15-1142 · Cited by 384
“While more sophisticated approaches have been proposed (Dhillon et al., 2011; Huang et al., 2012; Faruqui and Dyer, 2014; Levy and Goldberg, 2014; Yang and Eisen-stein, 2015), Word2Vec remains a popular choice due to their efficiency and simplicity.”
BackgroundSelf-citationLearning principled bilingual mappings of word embeddings while preserving monolingual invariance
Artetxe, M., Labaka, G., & Agirre, E. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1250 · Cited by 369
Towards Universal Paraphrastic Sentence Embeddings
Wieting, J., Bansal, M., Gimpel, K., & Livescu, K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.08198 · Cited by 103
“We tune over the strategy in our experiments.”
BackgroundMethodDomain Adaptation for Visual Applications: A Comprehensive Survey
Csurka, G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05374 · Cited by 246
“We can also have multi-view situations even when the views have the same data modalities (textual, visual, audio), such as in the case of parallel texts in different languages [236, 79], photos of the same person taken across different poses, illuminations and expressions [261, 195, 196, 170].”
BackgroundBilingual Word Representations with Monolingual Quality in Mind
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing · doi:10.3115/v1/w15-1521 · Cited by 315
“Past work such as (Pennington et al., 2014; Faruqui and Dyer, 2014) among many others, have demonstrated that higher word similarity scores can be achieved by simply increasing the vocabulary coverage, training corpus size, and the embedding di-mension.”
BackgroundAn Autoencoder Approach to Learning Bilingual Word Representations
P, S. C. A., Lauly, S., Larochelle, H., Khapra, M. M., Ravindran, B., Raykar, V. C., & Saha, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1402.1454 · Cited by 309
“While the majority of previous work on vectorial text representations has concentrated on the monolingual case, there has also been considerable interest in learning word and document representations that are aligned across languages [6, 7, 8, 9, 10, 11, 12].”
BackgroundBilBOWA: Fast Bilingual Distributed Representations without Word Alignments
Gouws, S., Bengio, Y., & Corrado, G. S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.2455 · Cited by 285
“It was extended by Faruqui et al. [9], who simultanteously projected source and target language embeddings into a joint space using canonical correlation analysis.”
MethodXTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
Hu, J., Ruder, S., Siddhant, A., Neubig, G., Fırat, O., & Johnson, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11080 · Cited by 278
“Over the last few years, there has been a move towards general-purpose multilingual representations that are applicable to many tasks, both on the word level (Mikolov et al., 2013; Faruqui & Dyer, 2014; Artetxe et al., 2017) or the full-sentence level (Devlin et al., 2019; Lample & Conneau, 2019).”
BackgroundGromov-Wasserstein Alignment of Word Embedding Spaces
Alvarez-Melis, D., & Jaakkola, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1214 · Cited by 275
“1889 mon space on which to project both sets of embeddings (Faruqui and Dyer, 2014; Lu et al., 2015).”
BackgroundA Survey of Cross-lingual Word Embedding Models
Ruder, S., Vulić, I., & Søgaard, A. (2019) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.11640 · Cited by 266
“Faruqui and Dyer (2014) later applied CCA to project words from two languages into a shared embedding space.”
BackgroundMethodInfluentialMassively Multilingual Word Embeddings
Ammar, W., Mulcaire, G., Tsvetkov, Y., Lample, G., Dyer, C., & Smith, N. A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.01925 · Cited by 263
“Some previous work on bilingual and multilingual embeddings focuses on monolingual word similarity to evaluate embeddings (e.g., Faruqui and Dyer, 2014).”
BackgroundMethodInfluentialSelf-citationKoehn, P. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108608480 · Cited by 236
Adversarial Training for Unsupervised Bilingual Lexicon Induction
Zhang, M., Liu, Y., Luan, H., & Sun, M. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1179 · Cited by 256
“…2016), or word level (i.e. seed lexicon) (Gouws and Søgaard, 2015; Wick et al., 2016; Duong et al., 2016; Shi et al., 2015; Mikolov et al., 2013a; Dinu et al., 2015; Lazaridou et al., 2015; Faruqui and Dyer, 2014; Lu et al., 2015; Ammar et al., 2016; Zhang et al., 2016a, 2017; Smith et al., 2017).”
Problems With Evaluation of Word Embeddings Using Word Similarity Tasks
Faruqui, M., Tsvetkov, Y., Rastogi, P., & Dyer, C. (2016) · Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP · doi:10.18653/v1/w16-2506 · Cited by 246
“Faruqui and Dyer (2014b), and Lu et al. (2015) evaluate the word embeddings exclusively on word similarity and word analogy tasks.”
BackgroundSelf-citationMetaphor Detection with Cross-Lingual Model Transfer
Tsvetkov, Y., Boytsov, L., Gershman, A., Nyberg, E., & Dyer, C. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1024 · Cited by 227
“We employ 64-dimensional vector-space word representations constructed by Faruqui and Dyer (2014).”
MethodSelf-citationChen, M., Tian, Y., Chang, K.-W., Skiena, S., & Zaniolo, C. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/556 · Cited by 220
“Note that off-line multilingual word embedding models, including LM [ Mikolov et al. , 2013a ] , CCA [ Faruqui and Dyer, 2014 ] , and orthogonal-transformation-based OT [ Xing et al. , 2015 ] can also be extended to KGs, but are outperformed by MTransE on cross-lingual tasks.”
BackgroundArtetxe, M., Labaka, G., & Agirre, E. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11992 · Cited by 220
“We release our implementation as an open source project, which allows to replicate several previous methods as well as our improved variant (Mikolov, Le, and Sutskever 2013; Faruqui and Dyer 2014; Dinu, Lazaridou, and Baroni 2015; Shigeto et al. 2015; Xing et al. 2015; Zhang et al. 2016; Smith et al. 2017; Artetxe, La…”
MethodResultInfluentialTransfer learning for speech and language processing
Wang, D., & Zheng, T. F. (2015) · 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) · doi:10.1109/apsipa.2015.7415532 · Cited by 213
“A more systematic approach was proposed by [139], where different languages were projected to the same space by”
BackgroundURIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors
Littell, P., Mortensen, D. R., Lin, K., Kairis, K., Turner, C., & Levin, L. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2002 · Cited by 182
“The recent success of “polyglot” models (Hermann and Blunsom, 2014; Faruqui and Dyer, 2014; Ammar et al., 2016; Tsvetkov et al., 2016; Daiber et al., 2016), in which a language model is trained on multiple languages and shares representations across languages, represents a promising avenue for NLP,…”
BackgroundCross-lingual Dependency Parsing Based on Distributed Representations
Guo, J., Che, W., Yarowsky, D., Wang, H., & Liu, T. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1119 · Cited by 180
“The second approach we consider is similar to Faruqui and Dyer (2014), which use CCA to improve monolingual word embeddings with multilingual correlation.”
MethodCross-lingual Models of Word Embeddings: An Empirical Comparison
Upadhyay, S., Faruqui, M., Dyer, C., & Roth, D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1157 · Cited by 177
“…incorporating cross-lingual distributional information (Klementiev et al., 2012; Zou et al., 2013; Vuli ´ c and Moens, 2013b; Mikolov et al., 2013b; Faruqui and Dyer, 2014; Hermann and Blunsom, 2014; Chandar et al., 2014, inter alia ), with improvements observed both on monolingual (Faruqui and…”
BackgroundMethodInfluentialSelf-citationGlavaš, G., Litschko, R., Ruder, S., & Vulić, I. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1070 · Cited by 180
“Faruqui and Dyer (2014) use CCA to project XL1 and XL2 obtain monolingual vectors) and b) they do not require any multilingual corpora, they lend themselves to a wider spectrum of languages than the alternatives (Ruder et al., 2018b).”
BackgroundMethodVisualizing and Understanding Neural Machine Translation
Ding, Y., Liu, Y., Luan, H., & Sun, M. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1106 · Cited by 168
“Though projecting word embedding space into two dimensions (Faruqui and Dyer, 2014) and the attention matrix (Bahdanau et al.”
BackgroundMrkšić, N., Vulić, I., Séaghdha, D. Ó., Leviant, I., Reichart, R., Gašić, M., Korhonen, A., & Young, S. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00063 · Cited by 170
“English words which map to the same Irish word are likely to be synonyms, even if those English pairs are not present in the PPDB datasets (Faruqui and Dyer, 2014).”
Unsupervised Multilingual Word Embeddings
Chen, X., & Cardie, C. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1024 · Cited by 166
“These embeddings have been found beneficial for a number of cross-lingual and even monolingual NLP tasks (Faruqui and Dyer, 2014; Ammar et al., 2016).”
BackgroundNeural Cross-Lingual Named Entity Recognition with Minimal Resources
Xie, J., Yang, Z., Neubig, G., Smith, N. A., & Carbonell, J. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1034 · Cited by 222
Sparse Overcomplete Word Vector Representations
Faruqui, M., Tsvetkov, Y., Yogatama, D., Dyer, C., & Smith, N. A. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1144 · Cited by 157
“Faruqui and Dyer (2014) learned vectors by first performing SVD on text in different languages, then applying canonical correlation analysis on pairs of vectors for words that align in parallel corpora.”
MethodSelf-citationCheap Translation for Cross-Lingual Named Entity Recognition
Mayhew, S., Tsai, C.-T., & Roth, D. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1269 · Cited by 142
“We tried several ideas for gathering a mapping for this shared vocabulary: manual mapping, edit-distance mapping, and cross-lingual CCA with word vectors.”
BackgroundSentence Representation Method Based on Multi-Layer Semantic Network
Zheng, W., Liu, X., & Yin, L. (2021) · Applied Sciences · doi:10.3390/app11031316 · Cited by 151
“(1) Word2vec technology [10] combined with GloVe-840B-300D [34] was used to train the word vector embedding representation of the dictionary database; (2) According to the word’s position in the dictionary, the embedding vector w corresponding to each word in the sentence is obtained wi ∈ Rdw×1.”
BackgroundMethodCross-Lingual Word Embeddings for Low-Resource Language Modeling
Adams, O., Makarucha, A. J., Neubig, G., Bird, S., & Cohn, T. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1088 · Cited by 163
“, 2016), while others use bilingual dictionaries (Mikolov et al., 2013b; Xiao and Guo, 2014; Faruqui and Dyer, 2014; Gouws and Sogaard, 2015; Duong et al., 2016; Ammar et al., 2016), or neither (Valerio and Barone, 2016).”
BackgroundNi, J., Dinu, G., & Florian, R. (2017) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p17-1135 · Cited by 141
“One approach builds monolingual representations separately and then brings them to the same space typically using a seed dictionary (Mikolov et al., 2013b; Faruqui and Dyer, 2014).”
BackgroundDeep Multilingual Correlation for Improved Word Embeddings
Lu, A., Wang, W., Bansal, M., Gimpel, K., & Livescu, K. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1028 · Cited by 134
“For their baseline, Faruqui and Dyer (2014) For example, the WS-353 correlation improves from 46.7 to 67.1, essentially matching the linear CCA correlations, though DCCA still outperforms them both.”
BackgroundMethodInfluentialEarth Mover's Distance Minimization for Unsupervised Bilingual Lexicon Induction
Zhang, M., Liu, Y., Luan, H., & Sun, M. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1207 · Cited by 170
“…level (i.e. in the form of seed lexicon) (Gouws and Søgaard, 2015; Wick et al., 2016; Duong et al., 2016; Shi et al., 2015; Mikolov et al., 2013a; Faruqui and Dyer, 2014; Lu et al., 2015; Dinu et al., 2015; Lazaridou et al., 2015; Ammar et al., 2016; Zhang et al., 2016a, 2017; Smith et al.,…”
Background(Almost) Zero-Shot Cross-Lingual Spoken Language Understanding
Upadhyay, S., Faruqui, M., Tür, G., Hakkani-Tur, D. Z., & Heck, L. P. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461905 · Cited by 116
Self-citationLearning Crosslingual Word Embeddings without Bilingual Corpora
Duong, L., Kanayama, H., Ma, T., Bird, S., & Cohn, T. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1136 · Cited by 113
“Mikolov et al. (2013a) and Faruqui and Dyer (2014) use a cascade style of training where the word embeddings in both source and target language are trained separately and then combined later using the dictionary.”
BackgroundAutomated Geocoding of Textual Documents: A Survey of Current Approaches
Melo, F., & Martins, B. (2016) · Transactions in GIS · doi:10.1111/tgis.12212 · Cited by 142
“Having cross-lingual representations (Soyer et al. 2015; Faruqui and Dyer 2014) can also be of particular interest in the task of document geocoding, given that training datasets for languages other than English will be smaller in size, and thus by transferring knowledge from existing English corpora we can perhaps si…”
BackgroundBilingual Distributed Word Representations from Document-Aligned Comparable Data
Vulić, I., & Moens, M. (2016) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4986 · Cited by 132
Unsupervised Cross-lingual Transfer of Word Embedding Spaces
Xu, R., Yang, Y., Otani, N., & Wu, Y. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1268 · Cited by 121
“Supervised Methods: There is a rich body of supervised methods for learning cross-lingual transfer of word embeddings based on bilingual dictionaries (Mikolov et al., 2013; Faruqui and Dyer, 2014; Artetxe et al., 2016; Xing et al., 2015; Duong et al., 2016; Gouws and Søgaard, 2015), sentence-aligned corpora (Kočiskỳ e…”
BackgroundInfluentialNeural Adaptation Layers for Cross-domain Named Entity Recognition
Lin, B. Y., & Lu, W. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1226 · Cited by 122
“Although there are alternative methods that also learn a mapping between embeddings learned from different domains (Faruqui and Dyer, 2014; Artetxe et al., 2016; Smith et al., 2017), such methods usually involve modifying source domain embeddings, and thus re-training of the source model based on…”
MethodCross-lingual Wikification Using Multilingual Embeddings
Tsai, C.-T., & Roth, D. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1072 · Cited by 110
The Role of Context Types and Dimensionality in Learning Word Embeddings
Melamud, O., McClosky, D., Patwardhan, S., & Bansal, M. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1118 · Cited by 110
“4) Sentiment Analysis (SENTI) Following Faruqui et al. (2014), we used a sentence-level binary decision version of the sentiment analysis task from Socher et al. (2013).”
BackgroundMethodInfluentialTen Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings
Zhang, Y., Gaddy, D., Barzilay, R., & Jaakkola, T. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1156 · Cited by 107
“Multilingual Word Embeddings There is an expansive body of research on learning multilingual word embeddings (Gouws et al., 2014; Faruqui and Dyer, 2014; Lu et al., 2015; Lauly et al., 2014; Luong et al., 2015).”
BackgroundA survey of cross-lingual embedding models.
Ruder, S. (2017) · Cited by 121
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces
Patra, B., Moniz, J. R. A., Garg, S., Gormley, M. R., & Neubig, G. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1018 · Cited by 130
“Since then, several approaches have been proposed for learning bilingual dictionaries (Faruqui and Dyer, 2014; Zou et al., 2013; Xing , 2015).”
BackgroundDo We Really Need Fully Unsupervised Cross-Lingual Embeddings?
Vulić, I., Glavaš, G., Reichart, R., & Korhonen, A. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1449 · Cited by 125
“Originally, the seed dictionaries typically spanned several thousand word pairs (Mikolov et al., 2013a; Faruqui and Dyer, 2014; Xing et al., 2015), but more recent work has shown that CLWEs can be induced with even weaker supervision from small dictionaries spanning several hundred pairs (Vulić and Korhonen, 2016), id…”
BackgroundOn the Role of Seed Lexicons in Learning Bilingual Word Embeddings
Vulić, I., & Korhonen, A. (2016) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p16-1024 · Cited by 99
“All Type 4 models (Mikolov et al., 2013a; Faruqui and Dyer, 2014; Dinu et al., 2015; Lazaridou et al., 2015) rely on readily available seed lexicons of highly frequent words obtained by e.g. Google Translate (GT) to learn the mapping (again colliding with P2), but they are able to satisfy P1.”
BackgroundMethodDeep Learning in Sentiment Analysis: Recent Architectures
Abdullah, T., & Ahmet, A. (2022) · ACM Computing Surveys · doi:10.1145/3548772 · Cited by 134
“Dual mono-lingual embeddings with bilingual dictionaries [43] are used to perform canonical correlation analysis to produce a shared vector space.”
MethodCommunity Evaluation and Exchange of Word Vectors at wordvectors.org
Faruqui, M., & Dyer, C. (2014) · Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.3115/v1/p14-5004 · Cited by 92
“Faruqui and Dyer (2014) propose a method based on canonical correlation analysis to produce more informed monolingual vectors using multilingual knowledge.”
BackgroundSelf-citationBarone, A. V. M. (2016) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w16-1614 · Cited by 123
“…representations that are compatible across multiple languages, either by learning mappings between different embedding spaces (Mikolov et al., 2013a; Faruqui and Dyer, 2014) or by jointly training cross-lingual representations (Klementiev et al., 2012; Hermann and Blunsom, 2013; Chandar et al.,…”
BackgroundMethodA Representation Learning Framework for Multi-Source Transfer Parsing
Guo, J., Che, W., Yarowsky, D., Wang, H., & Liu, T. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10352 · Cited by 93
“…representations focused solely on bilingual scenario (Kle-mentiev, Titov, and Bhattarai 2012; Zou et al. 2013; Xiao and Guo 2014; Chandar et al. 2014; Hermann and Blunsom 2014; Faruqui and Dyer 2014; Gouws, Bengio, and Cor-rado 2014; Lu et al. 2015; Luong, Pham, and Manning 2015; Guo et al. 2015).”
BackgroundExtending Multilingual BERT to Low-Resource Languages
Wang, Z., K, K., Mayhew, S., & Roth, D. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.240 · Cited by 90
Learning Multiview Embeddings of Twitter Users
Benton, A., Arora, R., & Dredze, M. H. (2016) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p16-2003 · Cited by 87
“Dense, low-dimensional vector representations (embeddings) have a long history in NLP, and recent work on neural models have provided new and popular algorithms for training representations for word types (Mikolov et al., 2013; Faruqui and Dyer, 2014), sentences (Kiros et al.”
BackgroundUnsupervised Cross-Modal Alignment of Speech and Text Embedding SpacesPreprint
Chung, Y.-A., Weng, W., Tong, S., & Glass, J. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07467 · Cited by 95
“Inspired by the notion, several studies have focused on designing algorithms that exploit this similarity to learn a cross-lingual alignment between the embedding spaces of two languages, where the two embedding spaces are trained from independent text corpora [6, 7, 8, 9, 10, 11, 12].”
MethodMultiview LSA: Representation Learning via Generalized CCA
Rastogi, P., Durme, B. V., & Arora, R. (2015) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.3115/v1/n15-1058 · Cited by 96
“, 2014) 8 or two sources of cooccurrence statistics (Zou et al., 2013; Faruqui and Dyer, 2014; Bansal et al., 2014; Levy and Goldberg, 2014) 9 or using multi-modal data (Hill and Korhonen, 2014; Bruni et al.”
BackgroundMultilingual Hierarchical Attention Networks for Document ClassificationPreprint
Pappas, N., & Popescu-Belis, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.00896 · Cited by 96
“The goal is to learn an aligned word embedding space for multiple languages by leveraging bilingual dictionaries (Faruqui and Dyer, 2014; Ammar et al., 2016), parallel sentences (Gouws et al., 2015) or comparable documents such as Wikipedia pages (Yih et al., 2011; Al-Rfou et al., 2013).”
BackgroundMogadala, A., & Rettinger, A. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1083 · Cited by 80
“Methods in the Table 1 that use word-aligned parallel corpus as offline alignment (Mikolov et al., 2013b; Faruqui and Dyer, 2014) assume single correspondence between the words across languages and ignore polysemy.”
MethodInformation Retrieval: Advanced Topics and Techniques
(2024) · ACM eBooks · doi:10.1145/3674127 · Cited by 88
Learning Bilingual Word Representations by Marginalizing Alignments
Kočiský, T., Hermann, K. M., & Blunsom, P. (2014) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.3115/v1/p14-2037 · Cited by 81
Incrementally Learning the Hierarchical Softmax Function for Neural Language Models
Peng, H., Li, J., Song, Y., & Liu, Y. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10994 · Cited by 78
“Specifically, we use the datasets collected by Faruqui and Dyer (Faruqui and Dyer 2014) which include MC-30, TR-3k, MTurk-287, MTurk-771, RG-65, RW-STANFORD (RW), SIMLEX-999, VERB-143, WS-353-ALL, WS-353-REL, WS-353-SIM, and YP-130.”
MethodFrom static to dynamic word representations: a survey
Wang, Y., Hou, Y., Che, W., & Liu, T. (2020) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-020-01069-8 · Cited by 102
“Faruqui and Dyer [29] proposed another way to project embeddings from both source and target languages to a shared space with canonical correlation analysis (CCA).”
BackgroundConcatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations
Rücklé, A., Eger, S., Peyrard, M., & Gurevych, I. (2018) · TUbilio (Technical University of Darmstadt) · doi:10.48550/arxiv.1803.01400 · Cited by 76
“Common practice is to learn a mapping be-tween two monolingual word embedding spaces (Faruqui and Dyer, 2014; Artetxe et al., 2016).”
BackgroundLearning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach
Jawanpuria, P., Balgovind, A., Kunchukuttan, A., & Mishra, B. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00257 · Cited by 87
“Faruqui and Dyer (2014) use Canonical Correlation Analysis (CCA) to learn linear projections from the source and target languages to a common space such that correlations between the embeddings projected to this space are maximized.”
BackgroundPolyglot Contextual Representations Improve Crosslingual Transfer
Mulcaire, P., Kasai, J., & Smith, N. A. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1392 · Cited by 90
“State-of-the-art methods for crosslingual transfer make use of multilingual word embeddings, and much research has explored methods that align vector spaces for words in different languages (Faruqui and Dyer, 2014; Upadhyay et al., 2016; Ruder et al., 2017).”
BackgroundCross-lingual Structure Transfer for Relation and Event Extraction
Subburathinam, A., Lu, D., Ji, H., May, J., Chang, S.-F., Sil, A., & Voss, C. R. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1030 · Cited by 95
“, 2017) or canonical correlation analysis (CCA) (Ammar et al., 2016; Faruqui and Dyer, 2014; Lu et al., 2015) to transfer surface features across languages, our major innovation is to convert the text data into structured representations derived from universal dependency parses and enhanced with distributional informa…”
BackgroundBERT is Not an Interlingua and the Bias of Tokenization
Singh, J., McCann, B., Socher, R., & Xiong, C. (2019) · Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo) · doi:10.18653/v1/d19-6106 · Cited by 108
“…(Klementiev et al., 2012; Zou et al., 2013; Hermann and Blunsom, 2014) and then aligned using dictionaries between languages (Mikolov et al., 2013a; Faruqui and Dyer, 2014), and crosslingual embeddings can be learned jointly through entirely unsupervised methods (Conneau et al., 2017; Artetxe et…”
BackgroundMethodZero-Shot Cross-lingual Classification Using Multilingual Neural Machine TranslationPreprint
Eriguchi, A., Johnson, M., Fırat, O., Kazawa, H., & Macherey, W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.04686 · Cited by 92
“Obtaining representations from word level alignments - bilingual dictionaries or automatically generated word alignments - is the most popular approach (Mikolov et al. 2013; Faruqui and Dyer 2014; Zou et al. 2013).”
BackgroundEspaña-Bonet, C., Varga, A. C., Barrón‐Cedeño, A., & van Genabith, J. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2764273 · Cited by 73
“To some extent, it can be thought as a generalisation of methods that project monolingual embeddings in two different languages into a common space to obtain bilingual word embed-dings (Mikolov et al., 2013; Faruqui and Dyer, 2014; Madhyastha and Espa˜na-Bonet, 2016).”
BackgroundA Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
Levy, O., Søgaard, A., & Goldberg, Y. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1072 · Cited by 69
“Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 765–774, Valencia, Spain, April 3-7, 2017. c©2017 Association for Computational Linguistics”
BackgroundInfluentialNeural machine translation: Challenges, progress and future
Zhang, J., & Zong, C. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1632-x · Cited by 117
“Since [91] found that word embeddings from two languages can be mapped using some seed translation pairs, bilingual word embedding learning or bilingual lexicon induction has attracted more and more attention [4, 21, 31, 41, 158, 159].”
BackgroundNeural Cross-Lingual Entity Linking
Sil, A., Kundu, G., Florian, R., & Hamza, W. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11964 · Cited by 87
Inferring Affective Meanings of Words from Word Embedding
Li, M., Lu, Q., Long, Y., & Gui, L. (2017) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2723012 · Cited by 74
“More comprehensive studies use more kinds of contexts and knowledge base are explored to improve word embedding including the use of cross-lingual context [59], word definition context, knowledge base context [60], morphology context [61], and word embedding frommulti-views ormulti-resources [62], [63].”
BackgroundEvaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation
Siddhant, A., Johnson, M., Tsai, H., Arivazhagan, N., Riesa, J., Bapna, A., Fırat, O., & Raman, K. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6414 · Cited by 54
Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing
Zhang, Y., & Barzilay, R. (2015) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d15-1213 · Cited by 61
“We use the CCA method (Faruqui and Dyer, 2014) to generate multilingual word embeddings.”
MethodA Survey of Cross-lingual Sentiment Analysis: Methodologies, Models and Evaluations
Xu, Y., Cao, H., Du, W., & Wang, W. (2022) · Data Science and Engineering · doi:10.1007/s41019-022-00187-3 · Cited by 87
“…relying on expensive manually annotated corpora between source language and target language, such as cross-lingual parallel corpora or seed dictionary of word-level alignment [34], sentence-level alignment [35], and document-level alignment [36] served as cross-lingual supervised information.”
MethodSeparated by an Un-common Language: Towards Judgment Language Informed Vector Space ModelingPreprint
Leviant, I., & Reichart, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.00106 · Cited by 82
“Recent research on multilingual approaches to VSMs aim to exploit the impact of multilingual training.”
BackgroundRetrofitting Word Vectors to Semantic LexiconsPreprint
Faruqui, M., Dodge, J., Jauhar, S. K., Dyer, C., Hovy, E. H., & Smith, N. A. (2014) · arXiv (Cornell University) · doi:10.1184/r1/6473660 · Cited by 247
Self-citationSynthetic Treebanking for Cross-Lingual Dependency Parsing
Tiedemann, J., & Agić, Ż. (2016) · Journal of Artificial Intelligence Research · doi:10.1613/jair.4785 · Cited by 59
“Faruqui and Dyer (2014) use canonical correlation analysis to find cross-lingual projections of monolingual vector space models.”
BackgroundInfluentialPolyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning
Tsvetkov, Y., Sitaram, S., Faruqui, M., Lample, G., Littell, P., Mortensen, D. R., Black, A. W., Levin, L. S., & Dyer, C. (2016) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n16-1161 · Cited by 71
“…recent models that use distributed representations—in particular models that share representations across languages (Hermann and Blunsom, 2014; Faruqui and Dyer, 2014; Huang et al., 2015; Lu et al., 2015, inter alia )—suggest universal models applicable to multiple languages are a possibility.”
BackgroundSelf-citationStochastic optimization for deep CCA via nonlinear orthogonal iterations
Wang, W., Arora, R., Livescu, K., & Srebro, N. (2015) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2015.7447071 · Cited by 62
“multiple measurement modalities, such as simultaneously recorded audio + video [8], [9], audio + articulation [10], images + text [11], [12], [13], or parallel text in two languages [14], [15], [16], [17], [18], but may also be different information extracted from the same source, such”
BackgroundLearning Cross-lingual Word Embeddings via Matrix Co-factorization
Shi, T., Liu, Z., Liu, Y., & Sun, M. (2015) · doi:10.3115/v1/p15-2093 · Cited by 59
“Further, studies have shown that using cross-lingual correlation can improve the quality of word representations trained solely with monolingual corpora (Faruqui and Dyer, 2014).”
BackgroundXLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question AnsweringPreprint
Singh, J., McCann, B., Keskar, N. S., Xiong, C., & Socher, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11471 · Cited by 93
“…work that seeks to leverage multilingual data attempts to first train word embeddings from monolingual corpora (Klementiev et al., 2012; Zou et al., 2013; Hermann and Blunsom, 2014) and then align those embeddings using dictionaries be-tween languages (Mikolov et al., 2013a; Faruqui and Dyer, 2014).”
BackgroundOn the Linearity of Semantic Change: Investigating Meaning Variation via Dynamic Graph Models
Eger, S., & Mehler, A. (2016) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p16-2009 · Cited by 72
“An alternative to our second-order embeddings is to project vectors from different time periods in a common space (Mikolov et al., 2013a; Faruqui and Dyer, 2014), which requires to find corresponding terms across time.”
BackgroundImproving Cross-Lingual Word Embeddings by Meeting in the Middle
Doval, Y., Camacho-Collados, J., Espinosa-Anke, L., & Schockaert, S. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1027 · Cited by 64
“…this paper, attempts to learn bilingual embeddings via a two-step process: first, word embeddings are trained on monolingual corpora and then the resulting monolingual spaces are aligned by taking advantage of bilingual dictionaries (Mikolov et al., 2013b; Faruqui and Dyer, 2014; Xing et al., 2015).”
BackgroundMethodInfluentialLanguage-Agnostic Visual-Semantic Embeddings
Wehrmann, J., Lopes, M. A., Souza, D. M., & Barros, R. C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00590 · Cited by 54
“eral papers have proposed algorithms for cross-language alignment [11, 42, 2, 34, 3, 4, 6].”
BackgroundFILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
Fang, Y., Wang, S., Gan, Z., Sun, S., & Liu, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i14.17512 · Cited by 68
Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization
Flek, L., & Gurevych, I. (2016) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p16-1191 · Cited by 56
“Moreover, the coarse semantic categorization contained in su-persenses was shown to be preserved in translation (Schneider et al., 2013), making them a perfect candidate for a multilingual adaptation of the vector space, e.g. extending Faruqui and Dyer (2014).”
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.