Bilingual Lexicon Induction by Learning to Combine Word-Level and
            Character-Level Representations

Heyman, Geert; Vulić, Ivan; Moens, Marie‐Francine

doi:10.18653/v1/e17-1102

Cited by 29 publications

(54 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, the bootstrapping technique developed for traditional context-counting approaches (Peirsman & Padó, 2010;Vulić & Moens, 2013b) is an important predecessor to recent iterative self-learning techniques used to limit the bilingual dictionary seed supervision needed in mapping-based approaches (Hauer, Nicolai, & Kondrak, 2017;?). The idea of CCA-based word embedding learning (see later in Section 6) (Faruqui & Dyer, 2014b;Lu, Wang, Bansal, Gimpel, & Livescu, 2015) was also introduced a decade earlier (Haghighi, Liang, Berg-Kirkpatrick, & Klein, 2008); their word additionally discussed the idea of combining orthographic subword features with distributional signatures for cross-lingual representation learning: This idea re-entered the literature recently (Heyman, Vulić, & Moens, 2017), only now with much better performance.…”

Section: A Brief History Of Cross-lingual Word Representationsmentioning

confidence: 99%

A Survey of Cross-lingual Word Embedding Models

Ruder¹,

Vulić²,

Søgaard³

2019

jair

Self Cite

468

330

View full text Add to dashboard Cite

Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.

show abstract

Section: A Brief History Of Cross-lingual Word Representationsmentioning

confidence: 99%

A Survey of Cross-lingual Word Embedding Models

Ruder¹,

Vulić²,

Søgaard³

2019

jair

Self Cite

468

330

View full text Add to dashboard Cite

show abstract

“…Furthermore, the model that combines character-level information and word-level information outperforms other baselines (including BWESG, the strongest word-level model) by a margin. For more details, see Reference [58].…”

Section: Combining Word-level and Character-level Representationsmentioning

confidence: 99%

Improving the Translation Environment for Professional Translators

et al. 2019

Self Cite

View full text Add to dashboard Cite

When using computer-aided translation systems in a typical, professional translation workflow, there are several stages at which there is room for improvement. The SCATE (Smart Computer-Aided Translation Environment) project investigated several of these aspects, both from a human-computer interaction point of view, as well as from a purely technological side. This paper describes the SCATE research with respect to improved fuzzy matching, parallel treebanks, the integration of translation memories with machine translation, quality estimation, terminology extraction from comparable texts, the use of speech recognition in the translation process, and human computer interaction and interface design for the professional translation environment. For each of these topics, we describe the experiments we performed and the conclusions drawn, providing an overview of the highlights of the entire SCATE project.

show abstract

“…Especially BWEs obtained using post-hoc mapping (Mikolov et al, 2013b;Lazaridou et al, 2015) fail on this task. Consequently, Heyman et al (2017) build BWEs using aligned documents and then engineer a specialized classification-based approach to BLI. In contrast, our delightfully simple approach to create high-quality BWEs for the medical domain requires only monolingual data.…”

Section: Bilingual Lexicon Induction (Bli)mentioning

confidence: 99%

Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable

Hangya

Braune

Fraser

et al. 2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Bilingual tasks, such as bilingual lexicon induction and cross-lingual classification, are crucial for overcoming data sparsity in the target language. Resources required for such tasks are often out-of-domain, thus domain adaptation is an important problem here. We make two contributions. First, we test a delightfully simple method for domain adaptation of bilingual word embeddings. We evaluate these embeddings on two bilingual tasks involving different domains: cross-lingual twitter sentiment classification and medical bilingual lexicon induction. Second, we tailor a broadly applicable semi-supervised classification method from computer vision to these tasks. We show that this method also helps in low-resource setups. Using both methods together we achieve large improvements over our baselines, by using only additional unlabeled data.

show abstract

Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations

Cited by 29 publications

References 31 publications

A Survey of Cross-lingual Word Embedding Models

A Survey of Cross-lingual Word Embedding Models

Improving the Translation Environment for Professional Translators

Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable

Contact Info

Product

Resources

About