Cross-Lingual Bridges with Models of Lexical Borrowing

Tsvetkov, Yulia; Dyer, Chris

doi:10.1613/jair.4786

Cited by 18 publications

(12 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are, therefore, using the HRL as an intermediate pivot between the source LRL and English. Our experiments demonstrate that this significantly improves EL accuracy over directly linking to English, as named entities are likely similar in related languages (Tsvetkov and Dyer 2016). In Figure 1, the orthographic pivoting example shows that 'Poland' in Marathi and Hindi are written similarly and can be linked with our neural EL model.…”

Section: Introductionmentioning

confidence: 77%

Zero-Shot Neural Transfer for Cross-Lingual Entity Linking

Rijhwani

Xie

Neubig

et al. 2019

AAAI

View full text Add to dashboard Cite

Cross-lingual entity linking maps an entity mention in a source language to its corresponding entry in a structured knowledge base that is in a different (target) language. While previous work relies heavily on bilingual lexical resources to bridge the gap between the source and the target languages, these resources are scarce or unavailable for many low-resource languages. To address this problem, we investigate zero-shot cross-lingual entity linking, in which we assume no bilingual lexical resources are available in the source low-resource language. Specifically, we propose pivot-based entity linking, which leverages information from a highresource "pivot" language to train character-level neural entity linking models that are transferred to the source lowresource language in a zero-shot manner. With experiments on 9 low-resource languages and transfer through a total of 54 languages, we show that our proposed pivot-based framework improves entity linking accuracy 17% (absolute) on average over the baseline systems, for the zero-shot scenario. 1 Further, we also investigate the use of language-universal phonological representations which improves average accuracy (absolute) by 36% when transferring between languages that use different scripts.

show abstract

Section: Introductionmentioning

confidence: 77%

Zero-Shot Neural Transfer for Cross-Lingual Entity Linking

Rijhwani

Xie

Neubig

et al. 2019

AAAI

View full text Add to dashboard Cite

show abstract

“…Borrowed words-also called loan-words-constitute 10-70% of most language lexicons (Haspelmath, 2009); these are content words of foreign origin that are adapted in the language and are not perceived as foreign by language speakers. Computational modeling of cross-lingual transformations of loanwords is effective for inferring lexical correspondences across languages with limited parallel data, benefiting applications such as machine translation Tsvetkov and Dyer, 2016).…”

Section: Lexical Borrowingmentioning

confidence: 99%

“…To test this hypothesis, we augment the handengineered models proposed by Tsvetkov and Dyer (2016) with features from phone vectors learned by our model. Inputs to the borrowing framework are loanwords (in Swahili, Romanian, Maltese), and outputs are their corresponding "donor" words in the donor language (Arabic, French, Italian, resp.).…”

Section: Lexical Borrowingmentioning

confidence: 99%

See 1 more Smart Citation

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning

Tsvetkov

Sitaram

Faruqui

et al. 2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

Self Cite

View full text Add to dashboard Cite

We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to be predicted. We apply these to the problem of modeling phone sequences-a domain in which universal symbol inventories and cross-linguistically shared feature representations are a natural fit. Intrinsic evaluation on held-out perplexity, qualitative analysis of the learned representations, and extrinsic evaluation in two downstream applications that make use of phonetic features show (i) that polyglot models better generalize to held-out data than comparable monolingual models and (ii) that polyglot phonetic feature representations are of higher quality than those learned monolingually.

show abstract

“…In such cases, a resource rich, linguistically similar language is used as a proxy in order to perform the required NLP task. For example in Tsvetkov and Dyer (2015) the authors use Arabic, Italian and French as bridge languages to perform Swahili-English, Maltese-English and Romanian-English translations respectively.…”

Section: Embedding Similaritymentioning

confidence: 99%

Hypothesis Testing based Intrinsic Evaluation of Word Embeddings

Gurnani¹

2017

Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP

View full text Add to dashboard Cite

We introduce the cross-match test -an exact, distribution free, high-dimensional hypothesis test as an intrinsic evaluation metric for word embeddings. We show that cross-match is an effective means of measuring distributional similarity between different vector representations and of evaluating the statistical significance of different vector embedding models. Additionally, we find that cross-match can be used to provide a quantitative measure of linguistic similarity for selecting bridge languages for machine translation. We demonstrate that the results of the hypothesis test align with our expectations and note that the framework of two sample hypothesis testing is not limited to word embeddings and can be extended to all vector representations.

show abstract

Cross-Lingual Bridges with Models of Lexical Borrowing

Cited by 18 publications

References 74 publications

Zero-Shot Neural Transfer for Cross-Lingual Entity Linking

Zero-Shot Neural Transfer for Cross-Lingual Entity Linking

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning

Hypothesis Testing based Intrinsic Evaluation of Word Embeddings

Contact Info

Product

Resources

About