TAILIEUCHUNG - Báo cáo khoa học: "Character-Based Pivot Translation for Under-Resourced Languages and Domains"

In this paper we investigate the use of character-level translation models to support the translation from and to underresourced languages and textual domains via closely related pivot languages. Our experiments show that these low-level models can be successful even with tiny amounts of training data. We test the approach on movie subtitles for three language pairs and legal texts for another language pair in a domain adaptation task. Our pivot translations outperform the baselines by a large margin. . | Character-Based Pivot Translation for Under-Resourced Languages and Domains Jorg Tiedemann Department of Linguistics and Philology Uppsala University Uppsala Sweden Abstract In this paper we investigate the use of character-level translation models to support the translation from and to underresourced languages and textual domains via closely related pivot languages. Our experiments show that these low-level models can be successful even with tiny amounts of training data. We test the approach on movie subtitles for three language pairs and legal texts for another language pair in a domain adaptation task. Our pivot translations outperform the baselines by a large margin. 1 Introduction Data-driven approaches have been extremely successful in most areas of natural language processing NLP and can be considered the main paradigm in application-oriented research and development. Research in machine translation is a typical example with the dominance of statistical models over the last decade. This is even enforced due to the availability of toolboxes such as Moses Koehn et al. 2007 which make it possible to build translation engines within days or even hours for any language pair provided that appropriate training data is available. However this reliance on training data is also the most severe limitation of statistical approaches. Resources in large quantities are only available for a few languages and domains. In the case of SMT the dilemma is even more apparent as parallel corpora are rare and usually quite sparse. Some languages can be considered lucky for example because of political situations that lead to the production of freely available translated material on a large scale. A lot of research and development would not have been possible without the European Union and its language policies to give an example. One of the main challenges of current NLP research is to port data-driven techniques to underresourced languages which .

• Báo cáo khoa học
• Character Based Pivot Translation
• Under Resourced Languages and Domains
• Long Papers
• scientific reports
• model language
• process natural language
• Dialog Control
• Natural Language System
• Dialog Control in a Natural Language System
• Expanding the Horizons
• Natural Language Interfaces
• Phil Hayes
• PROSPECTS OR PRACTICAL
• NATURAL LANGUAGE SYSTEMS
• Workshops
• NATURAL LANGUAGE
• INTERACTION WITH MACHINES
• COMPUTER INTEBFACE DESIGN MURRAY TUROFF DEPARTMENT OF COMPUTER
• IiVFORMATION SCIENCE IIEW JERSEY INSTITUTE OF TECHNOLOGY
• EVALUATION OF NATURAL LANGUAGE
• INTERFACES TO DATABASE SYSTEMS
• A PANEL DISCUSSION
• database query system
• J
• Norwood Crout
• INTERFACES TO DATA BASE SYSTEMS
• Bozena Henisz
• INTERPRETING NATURAL LANGUAGE
• DATABASE UPDATES
• S
• Jermld Kaplan Jim David
• TRANSPORTABLE NATURAL LANGUAGE
• INTERFACES TO DATABASES
• Gary G
• Hendrlx and William H
• Lewis
• DATABASES THEORETICAL
• TECHNICAL ISSUES
• TRANSPORTABLE NATURAL LANGUAGE INTERFACES
• PROBLEMS AND TECHNIQUES
• Barbara J
• Grosz
• THEORETICAL TECHNICAL ISSUES
• NATURAL LANGUAGE ACCESS TO DATABASES
• R
• Petrick
• Domain Independent
• Database Access Systems
• ISSUES IN NATURAL LANGUAGE
• ACCESS TO DATABASES
• A LOGIC PROGRAMMING PERSPECTIVE
• Sharon C
• Salveter David Maier
• PLANNING NATURAL LANGUAGE
• EXPRESSIONS REFERRING
• Douglas E
• Appelt
• THE TEXT SYSTEM
• NATURAL LANGUAGE GENERATION
• Kathleen R
• M
• MENTING A DATABASE
• KNOWLEDGE REPRESENTATION
• THE KEY TO THE SELECTION PROBLEM
• E
• Jeffrey Conklin David D
• McDonald
• A KNOWLEDGE ENGINEERING
• NATURAL LANGUAGE UNDERSTANDING
• Stuart C
• Shapiro
• NATURAL LANGUAGE TEXTS
• NECESSARILY GRAMMATICAL
• EVEN COMPLETE
• UNGRAMHATICALITY
• EXTRA GRAMMATICALITY
• NATURAL LANGUAGE UNDERSTANDING SYSTEMS
• Taxonomy
• Descriptions
• Individuals in Natural
• Language Understanding
• The Use of Ooject Special Knowledge
• Natural Language Processing
• Mark H
• Bursteln