Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 93-117).

1. Introduction -- 2. Monolingual word embedding models -- 3. Cross-lingual word embedding models : typology -- 4. A brief history of cross-lingual word representations -- 4.1. Cross-lingual word representations using bilingual lexicons -- 4.2. Cross-lingual word embeddings and word alignments -- 4.3. Representations based on latent and explicit cross-lingual concepts -- 4.4. Summary

5. Word-level alignment models -- 5.1. Word-level alignment methods with parallel data -- 5.2. Word-level alignment methods with comparable data

6. Sentence-level alignment methods -- 6.1. Sentence-level methods with parallel data -- 6.2. Sentence alignment with comparable data

7. Document-level alignment models -- 7.1. Document alignment with comparable data

8. From bilingual to multilingual training -- 8.1. Multilingual word embeddings from word-level information -- 8.2. Multilingual word embeddings from sentence-level and document-level information

9. Unsupervised learning of cross-lingual word embeddings -- 9.1. Seed dictionary induction -- 9.2. Refinement and heuristics -- 9.3. Limitations of unsupervised approaches

10. Applications and evaluation -- 10.1. Intrinsic evaluation -- 10.2. Extrinsic evaluation through cross-lingual transfer -- 10.3. Multi-modal and cognitive approaches to evaluation

11. Useful data and software -- 11.1. Monolingual resources -- 11.2. Cross-lingual data -- 11.3. Cross-lingual word embedding models -- 11.4. Evaluation and application -- 12. General challenges and future directions.

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

INSPEC

Google scholar

Google book search

The majority of natural language processing (NLP) is English language processing, and while there is good language technology support for (standard varieties of) English, support for Albanian, Burmese, or Cebuano--and most other languages--remains limited. Being able to bridge this digital divide is important for scientific and democratic reasons but also represents an enormous growth potential. A key challenge for this to happen is learning to align basic meaning-bearing units of different languages. In this book, the authors survey and discuss recent and historical work on supervised and unsupervised learning of such alignments. Specifically, the book focuses on so-called cross-lingual word embeddings. The survey is intended to be systematic, using consistent notation and putting the available methods on comparable form, making it easy to compare wildly different approaches. In so doing, the authors establish previously unreported relations between these methods and are able to present a fast-growing literature in a very compact way. Furthermore, the authors discuss how best to evaluate cross-lingual word embedding methods and survey the resources available for students and researchers interested in this topic.

Also available in print.

Title from PDF title page (viewed on June 26, 2019).