Filters








6,471 Hits in 3.6 sec

A lexicon for knowledge-based MT

Boyan Onyshkevich, Sergei Nirenburg
1995 Machine Translation  
In knowledge-based machine translation (KBMT), the lexicon can be specified and acquired only in close connection with the specification and acquisition of the world model (ontology) and the specification  ...  Ontology Concepts Ontology Concepts Lexical Semantic Specification Lexical Syntactic Specification Ontology Concepts -4 - Organization of the Lexicon The lexicon for a given language is a collection of  ...  All lexical units are heads of entries in the MT lexicon for the source language.  ... 
doi:10.1007/bf00997231 fatcat:2tf7zb4qbrdqvlqsx6qocvcdj4

Two principles and six techniques for rapid MT development

Sergei Nirenburg, Stephen Beale, Stephen Helmreich, Kavi Mahesh, Evelyne Viegas, Rémi Zajac
1996 Conference of the Association for Machine Translation in the Americas  
In this paper we describe a range of techniques used at NMSU CRL for accelerating the development of MT systems.  ...  Then we illustrate a set of techniques for semi-automatic acquisition of static resources: (a) automatic induction of grammars, (b) corpus-based acquisition of bilingual glossaries, and automatic acquisition  ...  Our work continues to advance the framework of the Pangloss MT project (e.g., Nirenburg (ed.), 1994) , in which the word-for-word, glossary-based, transfer-based, knowledge-based and example-based translation  ... 
dblp:conf/amta/NirenburgBHMVZ96 fatcat:iizadpjebvavpg36a7bkiy4rse

MONNET: Multilingual Ontologies for Networked Knowledge

Mihael Arcan, Paul Buitelaar
2013 Machine Translation Summit  
The project outcomes can be described as a set of software components as follows, all of which can be used in combination as well as stand-alone:  ...  A hybrid machine translation (MT) approach has been explored that builds on state of the art statistical MT as provided by the open source Moses system, and knowledge-based approaches using domain knowledge  ...  The ontology-lexicon is represented on the basis of the "lemon" format, 2 a lexicon model for ontologies that has been defined by the Monnet project for the appropriate integration of lexical, linguistic  ... 
dblp:conf/mtsummit/ArcanB13 fatcat:pemyvrd3ojgllc2seengchvfci

Automated Translation Between Lexicon and Corpora

Elisabetta Gola, Stefano Federici, Nilda Ruimy, John Wade
2012 Humana.Mente: Journal of Philosophical Studies  
Then we will advocate the need for a richer lexicon in MT processes and sketch a methodology to obtain it through a mix of corpus-based and machine learning approaches.  ...  In this work we will show the role of lexical resources in machine translation processes, giving several examples after a brief overview of Machine Translation studies.  ...  ACKNOWLEDGEMENTS This work is the outcome of a collaborative effort.  ... 
doaj:2de6dc0ed94a48628ad6d3dd661dacf4 fatcat:7soefjhr4ffnxpsiy533evsl7u

Towards a Public Multilingual Knowledge Management Infrastructure for the European Digital Single Market

Peter Schmitz, Enrico Francesconi, Najeh Hajlaoui, Brahim Batouche
2017 International Conference on Language, Data, and Knowledge  
In particular it aims to create a set of tools and facilities, based on Semantic Web technologies, for establishing semantic interoperability between multilingual lexicons.  ...  A comparative study among the main data models for representing lexicons and recommendations for the PMKI service are reported.  ...  For instance users, such as specific-domain MT developers, can query a document collection in a specific language for a specific domain.  ... 
dblp:conf/ldk/0002FHB17 fatcat:cybbrgfbszecda4ec32m2qkx7a

What is Example-Based Machine Translation? [chapter]

Davide Turcato, Fred Popowich
2003 Text, Speech and Language Technology  
We make a proposal for translation knowledge bases that make such an overlap explicit.  ...  We maintain that the essential feature that characterizes a Machine Translation approach and sets it apart from other approaches is the kind of knowledge it uses.  ...  The evidence explicitly stated in a knowledge base is the same for the two approaches. The same knowledge base can be used by both. Where would EBMT and lexicalist MT differ then?  ... 
doi:10.1007/978-94-010-0181-6_2 fatcat:twhzi65a55hsje6zwl4wgubgye

wEBMT: Developing and Validating an Example-Based Machine Translation System Using the World Wide Web

Andy Way, Nano Gough
2003 Computational Linguistics  
We have developed an example-based machine translation (EBMT) system that uses the World Wide Web for two different purposes: First, we populate the system's memory with translations gathered from rule-based  ...  MT systems located on the Web.  ...  Acknowledgments The authors wish to thank Mary Hearne for helpful input in the initial stages of this project.  ... 
doi:10.1162/089120103322711596 fatcat:hsmnm5bc4jfkbnxmra6lr5h25y

Term Builder: a lexical knowledge acquisition tool for the Logos machine translation system

Brigitte Orliac, Kutz Arrieta
1999 Machine Translation Summit  
The new Logos 8 technology is based on a relational database for storage and organization of the lexical data.  ...  The new automatic coding functionality within Term-Builder is significantly improving the process of acquiring new lexicons for MT and other applications.  ...  Lexical knowledge in the Logos system is organized in a transparent, hierarchical, relationship-based model.  ... 
dblp:conf/mtsummit/OrliacA99 fatcat:luwyfwn5inehhccwb3zvmgzxiy

Automatically Creating Bilingual Lexicons for Machine Translation from Bilingual Text [article]

Davide Turcato (Simon Fraser University, TCC Communications, Canada)
1998 arXiv   pre-print
A method is presented for automatically augmenting the bilingual lexicon of an existing Machine Translation system, by extracting bilingual entries from aligned bilingual text.  ...  The proposed method only relies on the resources already available in the MT system itself.  ...  the Institute for Robotics and Intelligent Systems.  ... 
arXiv:cmp-lg/9807010v1 fatcat:4dfdi5nj2bhb7fmkmsrae5qhua

Page 208 of Computational Linguistics Vol. 19, Issue 1 [page]

1993 Computational Linguistics  
interfaces that allow for more rapid manual development of knowledge bases.  ...  CMT'’s feature-based lexicon structure is discussed in Chapter 4, along with some discussion on how lexicons might be constructed in a semi-automated fashion.  ... 

On Extracting Multiword NP Terminology for MT

Svetlana Sheremetyeva
2009 European Association for Machine Translation Conferences/Workshops  
The paper addresses the issue of MT knowledge acquisition and describes a new hybrid methodology for automatic extraction of multi-word nominal terminology.  ...  The approach is based on statistical techniques merged into a strongly lexicalized Constraint Grammar paradigm. It is targeted at intelligent output and computationally attractive properties.  ...  in MT lexicons.  ... 
dblp:conf/eamt/Sheremetyeva09 fatcat:i2la2c6x3rh6nkj5ohgmquxohi

Building resources for MT: What the user hasn't got we have to provide

Guðrún Magnúsdóttir
1995 Machine Translation Summit  
The typical MT-system lexicon will in fact give you the data needed for basic natural-language analysis.  ...  lack the knowledge needed for tuning the system to fit the in-house environment.  ... 
dblp:conf/mtsummit/Magnusdottir95 fatcat:dcadtjuqpzguboyd57ga5ahm5u

Controlled Authoring In A Hybrid Russian-English Machine Translation System

Svetlana Sheremetyeva
2014 Proceedings of the 3rd Workshop on Hybrid Approaches to Machine Translation (HyTra)  
Implemented in a preediting tool the controlled authoring module can be stand-alone and pipelined to any foreign MT system.  ...  In this paper we describe the design and deployment of a controlled authoring module in REPAT, a hybrid Russian-English machine translation system for patent claims.  ...  The REPAT translation environment includes hybrid modules for source language analysis, controlled authoring, terminology management, knowledge development and rule-based modules for transfer and target  ... 
doi:10.3115/v1/w14-1004 dblp:conf/hytra/Sheremetyeva14 fatcat:vy3v2bi4orhx5mytbsstqhnfeq

On-The-Fly Translator Assistant (Readability and Terminology Handling)

Svetlana Sheremetyeva
2014 Proceedings of the EACL 2014 Workshop on Humans and Computer-assisted Translation  
The methodology is based on a language-independent hybrid extraction technique used for document analysis, and language-dependent shallow linguistic knowledge.  ...  The approach is illustrated by its implementation into a CAT tool for the Russian-English language pair. Such tools can also be integrated into full MT systems.  ...  The knowledge base contains shallow linguistic knowledge,lexicons and rules. The NP extractor is a hybrid stand-alone tool pipelined to the system.  ... 
doi:10.3115/v1/w14-0304 dblp:conf/eacl/Sheremetyeva14 fatcat:p2dovt262bdxno2zx4hmfmnske

Page 434 of Computational Linguistics Vol. 29, Issue 3 [page]

2003 Computational Linguistics  
We use an n-gram-based segmentation method. Initially, we located all possible bigrams, trigrams and so on within the input string and then searched for these within the relevant knowledge sources.  ...  of the Input In many cases, a 100% match for a given NP cannot be found in the phrasal lexicon.  ... 
« Previous Showing results 1 — 15 out of 6,471 results