Filters








678 Hits in 7.1 sec

Graph Exploration and Cross-lingual Word Embeddings for Translation Inference Across Dictionaries

Marta Lanau-Coronas, Jorge Gracia
2020 Zenodo  
To that end, we essayed two different types of techniques: based on graph exploration on the one hand and, on the other hand, based on cross-lingual word embeddings.  ...  This paper describes the participation of two different approaches in the 3rd Translation Inference Across Dictionaries (TIAD 2020) shared task.  ...  A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings.  ... 
doi:10.5281/zenodo.3898278 fatcat:4asperaxhzdflnlksnu6ybu3zy

Results of the Translation Inference Across Dictionaries 2019 Shared Task

Jorge Gracia, Besim Kabashi, Ilan Kernerman, Marta Lanau-Coronas, Dorielle Lonke
2019 Zenodo  
The objective of the Translation Inference Across Dictionaries (TIAD) shared task is to explore and compare methods and techniques that infer translations indirectly between language pairs, based on other  ...  in the Apertium RDF graph.  ...  Acknowledgements We would like to thank Michael Ruppert (University of Erlangen-Nuremberg) for his assistance with the Word2Vec baseline.  ... 
doi:10.5281/zenodo.3555154 fatcat:2yhcyak7lbh3vpp43cmw2n2pii

Translation Inference through Multi-lingual Word Embedding Similarity

Kathrin Donandt, Christian Chiarcos
2019 Zenodo  
This paper describes our contribution to the Shared Task on Translation Inference across Dictionaries (TIAD-2019).  ...  In our approach, we construct a multi-lingual word embedding space by projecting new languages in the feature space of a language for which a pretrained embedding model exists.  ...  Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors" funded in the European Union's Horizon 2020 research and innovation programme under grant agreement No 825182.  ... 
doi:10.5281/zenodo.3555183 fatcat:ky5avcys7vd4lglkyuqw3fpvfi

Word Translation Without Parallel Data [article]

Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou
2018 arXiv   pre-print
State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora.  ...  Our code, embeddings and dictionaries are publicly available.  ...  ACKNOWLEDGMENTS We thank Juan Miguel Pino, Moustapha Cissé, Nicolas Usunier, Yann Ollivier, David Lopez-Paz, Alexandre Sablayrolles, and the FAIR team for useful comments and discussions.  ... 
arXiv:1710.04087v3 fatcat:a2oivyteubglvgxear4rocvlc4

Robust Cross-Lingual Hypernymy Detection Using Dependency Context

Shyam Upadhyay, Yogarshi Vyas, Marine Carpuat, Dan Roth
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
We propose BISPARSE-DEP, a family of unsupervised approaches for cross-lingual hypernymy detection, which learns sparse, bilingual word embeddings based on dependency contexts.  ...  The ability to detect hypernymy cross-lingually can aid in solving cross-lingual versions of tasks such as textual entailment and event coreference.  ...  reviewers from EMNLP/CoNLL 2017 and NAACL 2018 for their constructive feedback.  ... 
doi:10.18653/v1/n18-1056 dblp:conf/naacl/UpadhyayVCR18 fatcat:qymnplvqsvcejlvhkzkhgfpp3e

Robust Cross-lingual Hypernymy Detection using Dependency Context [article]

Shyam Upadhyay, Yogarshi Vyas, Marine Carpuat, Dan Roth
2018 arXiv   pre-print
We propose BISPARSE-DEP, a family of unsupervised approaches for cross-lingual hypernymy detection, which learns sparse, bilingual word embeddings based on dependency contexts.  ...  The ability to detect hypernymy cross-lingually can aid in solving cross-lingual versions of tasks such as textual entailment and event coreference.  ...  reviewers from EMNLP/CoNLL 2017 and NAACL 2018 for their constructive feedback.  ... 
arXiv:1803.11291v1 fatcat:elghjtmb2na6rnucwugcyhup4q

LLOD-Driven Bilingual Word Embeddings Rivaling Cross-Lingual Transformers in Quality of Life Concept Detection from French Online Health Communities [chapter]

Katharina Allgaier, Susana Veríssimo, Sherry Tan, Matthias Orlikowski, Matthias Hartung
2021 Applications and Practices in Ontology Design, Extraction, and Reasoning  
Furthermore, in a comparative evaluation we find that our models based on bilingual word embeddings exhibit a high degree of complementarity with an approach that integrates machine translation and rule-based  ...  The framework capitalizes on supervised cross-lingual projection methods, so that labeled training data for a source language are sufficient and are not needed for target languages.  ...  Acknowledgments This work was funded by the Prêt-à-LLOD project within the European Union's Horizon 2020 research and innovation programme under grant agreement no. 825182.  ... 
doi:10.3233/ssw210037 fatcat:nvmixudmg5gy5naedlaezqlkbi

Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach [article]

Pratik Jawanpuria, Arjun Balgovind, Anoop Kunchukuttan, Bamdev Mishra
2018 arXiv   pre-print
We show that our approach outperforms previous approaches on the bilingual lexicon induction and cross-lingual word similarity tasks.  ...  We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary.  ...  posed latent space representation of multiple languages by sharing annotated resources across languages.  ... 
arXiv:1808.08773v3 fatcat:tkic4ej7drbc3glenbnop6wkja

LLOD-driven Bilingual Word Embeddings Rivaling Cross-lingual Transformers in Quality of Life Concept Detection from French Online Health Communities

Katharina Allgaier, Susana Veríssimo, Sherry Tan, Matthias Orlikowski, Matthias Hartung
2021 Zenodo  
Furthermore, in a comparative evaluation we find that our models based on bilingual word embeddings exhibit a high degree of complementarity with an approach that integrates machine translation and rule-based  ...  The framework capitalizes on supervised cross-lingual projection methods, so that labeled training data for a source language are sufficient and are not needed for target languages.  ...  Acknowledgments This work was funded by the Prêt-à-LLOD project within the European Union's Horizon 2020 research and innovation programme under grant agreement no. 825182.  ... 
doi:10.5281/zenodo.5011771 fatcat:3t6upx3orjcxzirw5vqsdwp3wu

Towards Unsupervised Speech-to-Text Translation [article]

Yu-An Chung and Wei-Hung Weng and Schrasing Tong and James Glass
2018 arXiv   pre-print
The framework initializes the ST system with a cross-modal bilingual dictionary inferred from the monolingual corpora, that maps every source speech segment corresponding to a spoken word to its target  ...  We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language and independent text  ...  A key principle behind these unsupervised MT approaches is to initialize a MT model with a bilingual dictionary inferred from monolingual corpora, without using cross-lingual signals [7, 8] .  ... 
arXiv:1811.01307v1 fatcat:67wrfk45tjbavlv5dt2kjyxvoi

Bilingual embeddings with random walks over multilingual wordnets

Josu Goikoetxea, Aitor Soroa, Eneko Agirre
2018 Knowledge-Based Systems  
Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation.  ...  Our experiments involve twelve cross-lingual word similarity and relatedness datasets in six lan- guage pairs covering four languages, and show that: 1) random walks over mul- tilingual wordnets improve  ...  Experiments Word similarity and relatedness are the most common evaluation methods to measure the quality of monolingual embeddings [38, 39, 4, 36, 10] , and we thus chose cross-lingual word similarity  ... 
doi:10.1016/j.knosys.2018.03.017 fatcat:yyconb4yujhcjhfahrcncrsnnq

Unsupervised Cross-lingual Image Captioning [article]

Jiahui Gao, Yi Zhou, Philip L. H. Yu, Shafiq Joty, Jiuxiang Gu
2021 arXiv   pre-print
Our method relies on (i) a cross-lingual scene graph to sentence translation process, which learns to decode sentences in the target language from a cross-lingual encoding space of scene graphs using a  ...  sentence parallel (bitext) corpus, and (ii) an unsupervised cross-modal feature mapping which seeks to map an encoded scene graph features from image modality to language modality.  ...  For relationship and attribute nodes, the cross-lingual mapping is still word-level mapping. Fig. 2 (a) illustrates the word-level mapping.  ... 
arXiv:2010.01288v2 fatcat:3ddbfbajefcivoqo4q73z634xi

Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT [article]

Shijie Wu, Mark Dredze
2019 arXiv   pre-print
We compare mBERT with the best-published methods for zero-shot cross-lingual transfer and find mBERT competitive on each task.  ...  A new release of BERT (Devlin, 2018) includes a model simultaneously pretrained on 104 languages with impressive performance for zero-shot cross-lingual transfer on a natural language inference task.  ...  Cross-lingual Word Embeddings. The quality of the cross-lingual space is essential for zero-shot cross-lingual transfer.  ... 
arXiv:1904.09077v2 fatcat:tvxheufrerhkhphamtxnokrpdu

A Survey of Cross-lingual Word Embedding Models

Sebastian Ruder, Ivan Vulić, Anders Søgaard
2019 The Journal of Artificial Intelligence Research  
We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.  ...  In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions.  ...  Acknowledgements We thank the anonymous reviewers and the editors for their valuable and comprehensive feedback.  ... 
doi:10.1613/jair.1.11640 fatcat:vwlgtzzmhfdlnlyaokx2whxgva

A Variational Autoencoding Approach for Inducing Cross-lingual Word Embeddings

Liangchen Wei, Zhi-Hong Deng
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
We propose a variational autoencoding approach for training bilingual word embeddings.  ...  Empirical results on the task of cross lingual document classification has shown that our method is effective.  ...  We would also like to thank the anonymous reviewers for their helpful comments.  ... 
doi:10.24963/ijcai.2017/582 dblp:conf/ijcai/WeiD17 fatcat:ejya3znqxbc4fdvg7ex4oi5yiy
« Previous Showing results 1 — 15 out of 678 results