Central Library

Normal view MARC view ISBD view

Cross-Lingual Word Embeddings [electronic resource] / by Anders Søgaard, Ivan Vulić, Sebastian Ruder, Manaal Faruqui.

By: Søgaard, Anders [author.].
Contributor(s): Vulić, Ivan [author.] | Ruder, Sebastian [author.] | Faruqui, Manaal [author.] | SpringerLink (Online service).
Material type: materialTypeLabelBookSeries: Synthesis Lectures on Human Language Technologies: Publisher: Cham : Springer International Publishing : Imprint: Springer, 2019Edition: 1st ed. 2019.Description: XI, 120 p. online resource.Content type: text Media type: computer Carrier type: online resourceISBN: 9783031021718.Subject(s): Artificial intelligence | Natural language processing (Computer science) | Computational linguistics | Artificial Intelligence | Natural Language Processing (NLP) | Computational LinguisticsAdditional physical formats: Printed edition:: No title; Printed edition:: No title; Printed edition:: No titleDDC classification: 006.3 Online resources: Click here to access online
Contents:
Preface -- Introduction -- Monolingual Word Embedding Models -- Cross-Lingual Word Embedding Models: Typology -- A Brief History of Cross-Lingual Word Representations -- Word-Level Alignment Models -- Sentence-Level Alignment Methods -- Document-Level Alignment Models -- From Bilingual to Multilingual Training -- Unsupervised Learning of Cross-Lingual Word Embeddings -- Applications and Evaluation -- Useful Data and Software -- General Challenges and Future Directions -- Bibliography -- Authors' Biographies.
In: Springer Nature eBookSummary: 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.
    average rating: 0.0 (0 votes)
No physical items for this record

Preface -- Introduction -- Monolingual Word Embedding Models -- Cross-Lingual Word Embedding Models: Typology -- A Brief History of Cross-Lingual Word Representations -- Word-Level Alignment Models -- Sentence-Level Alignment Methods -- Document-Level Alignment Models -- From Bilingual to Multilingual Training -- Unsupervised Learning of Cross-Lingual Word Embeddings -- Applications and Evaluation -- Useful Data and Software -- General Challenges and Future Directions -- Bibliography -- Authors' Biographies.

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.

There are no comments for this item.

Log in to your account to post a comment.