Filters








961 Hits in 5.6 sec

How to Account for Idiomatic German Support Verb Constructions in Statistical Machine Translation

Fabienne Cap, Manju Nirmal, Marion Weller, Sabine Schulte im Walde
2015 Proceedings of the 11th Workshop on Multiword Expressions  
We work on the German to English translation direction, for which the identification of support-verb constructions is challenging due to the relatively free word order of German.  ...  Support-verb constructions (i.e., multiword expressions combining a semantically light verb with a predicative noun) are problematic for standard statistical machine translation systems, because SMT systems  ...  Moreover, it was funded by the DFG grants Distributional Approaches to Semantic Relatedness and Models of Morphosyntax for Statistical Machine Translation, and the DFG Heisenberg Fellowship SCHU-2580/1  ... 
doi:10.3115/v1/w15-0903 dblp:conf/mwe/CapNWW15 fatcat:kzxs5cpgrrcmbftohjf5zdphi4

An Approach to Handle Idioms and Phrasal Verbs in EnglishTamil Machine Translation System

Thiruumeni P G, Anand Kumar M, Dhanalakshmi V, Soman K P
2011 International Journal of Computer Applications  
In this paper, we report our work on incorporating a technique to handle phrasal verbs and idioms for English to Tamil machine translation.  ...  This technique, proposed for English to Tamil machine translation system, can be incorporated with machine translation system for English to any language.  ...  The following section will give a clear idea of how this technique can be used in rule based and factored statistical machine translation.  ... 
doi:10.5120/3139-4328 fatcat:uhnrbsuqbvf7bbzqlbigr4yidm

Identifying Phrasemes via Interlingual Association Measures -- A Data-driven Approach on Dependency-parsed and Word-aligned Parallel Corpora [article]

Johannes Graën
2017 arXiv   pre-print
context) conference in Innsbruck.  ...  This is a preprint of the article "Identifying Phrasemes via Interlingual Association Measures" that was presented in February 2016 at the LeKo (Lexical combinations and typified speech in a multilingual  ...  The author likes to thank his colleagues Noah Bubenhofer, Simon Clematide and Samuel Läubli for discussions and proof-reading. Special thanks are owed to everyone who  ... 
arXiv:1709.08196v1 fatcat:s3i6svptefddlmf3ikbvfpci74

Idioms [article]

Manfred Sailer
2021 Zenodo  
The state of the art before the emergence of HPSG is presented, followed by a discussion of four types of HPSG approaches to idioms. A section on future research closes the discussion.  ...  I would not have been able to format this chapter without the support of the Language Science Press team, in particular Sebastian Nordhoff.  ...  I would like to thank Elizabeth Pankratz for comments and proofreading.  ... 
doi:10.5281/zenodo.5599850 fatcat:e3kdwe7in5a4lf6coclrnnffcq

VPCTagger: Detecting Verb-Particle Constructions With Syntax-Based Methods

István Nagy T., Veronika Vincze
2014 Proceedings of the 10th Workshop on Multiword Expressions (MWE)  
In this paper, we examine how syntactic parsers perform on this task and we introduce VPCTagger, a machine learning-based tool that is able to identify English VPCs in context.  ...  If a data-driven morphological parser or a syntactic parser is trained on a dataset annotated with extra information for VPCs, they will be able to identify VPCs in raw texts.  ...  For instance, in German and in Hungarian, the particle usually precedes the verb and they are spelt as one word, e.g. aufmachen (up.make) "to open" in German or kinyitni (out.open) "to open" in Hungarian  ... 
doi:10.3115/v1/w14-0803 dblp:conf/mwe/TV14 fatcat:p7rzt3ixmrcyhf4hcee57z2cde

La traducción automática en la formación de traductores

Astrid SCHMIDHOFER, Natalie MAIR
2018 CLINA Revista Interdisciplinaria de Traducción Interpretación y Comunicación Intercultural  
With the improvement of free, next-generation machine translation software based on neural networks, Departments for Translation Studies are faced with the question of how to react to this new reality.  ...  For this purpose, we have conducted an experiment in a General Translation class and a Specialised Translation class.  ...  In the beginning Google Translate was a statistical machine translation system.  ... 
doi:10.14201/clina201842163180 fatcat:3lh6xwuyyvaalmufsm3iuaamzm

Introduction to the special issue on multiword expressions: Having a crack at a hard nut

Aline Villavicencio, Francis Bond, Anna Korhonen, Diana McCarthy
2005 Computer Speech and Language  
In this special issue we include ten papers which propose a variety of approaches for finding and handling these expressions, both for building general purpose lexical resources and in the context of specific  ...  Their heterogeneous characteristics have proved a challenge to both linguistic and computational analysis. Their importance to language technology has long been recognised.  ...  Japanese compound nouns in the context of a machine translation task).  ... 
doi:10.1016/j.csl.2005.05.001 fatcat:s4ahmqjf6rcijjykb22ajqal24

Shallow Context Analysis for German Idiom Detection

Miriam Amin, Peter Fankhauser, Marc Kupietz, Roman Schneider
2021 Zenodo  
In order to differentiate between figurative and literal usage of verb-noun combinations for the shared task on the disambiguation of German Verbal Idioms issued for KONVENS 2021, we apply and extend an  ...  approach originally developed for detecting idioms in a dataset consisting of random ngram samples.  ...  ically constructing a lexicon of verb phrase idiomatic 2018. A distributional semantics model for idiom combinations.  ... 
doi:10.5281/zenodo.5769518 fatcat:eixb2ybqvjewhlorytlh2zk6sq

Multiword Expressions: Insights From A Multi-Lingual Perspective [chapter]

Manfred Sailer, Stella Markantonatou
2018 Zenodo  
In this introductory chapter, we present the basic concept of the volume at hand.  ...  Acknowledgements This book reflects a subset of the activities carried out in the ICT COST Action  ...  We have also seen how lexicalist theories such as LFG and HPSG attempt to develop tools to account for the more phrasal phenomena that we find in MWEs.  ... 
doi:10.5281/zenodo.1186597 fatcat:vvfyqc67ibfvznzhjl4vq7jz7q

PARSEME-It: an Italian corpus annotated with verbal multiword expressions

Johanna Monti, Maria Pia di Buono
2019 Italian Journal of Computational Linguistics  
Notably, MWEs are pervasive in natural languages but are particularly difficult to be handled by NLP tools because of their characteristics and idiomaticity.  ...  Although several studies have been devoted to this topic, to the best of our knowledge, our study is the first attempt to provide a general framework for the identification of VMWEs in running texts and  ...  We are particularly grateful to Federico Sangati who always supported the annotation team and actively took part in the planning and the implementation of the project.  ... 
doi:10.4000/ijcol.483 fatcat:537lh5k3qnh3rmymc3vippijoq

Multi-word Entity Classification in a Highly Multilingual Environment

Sophie Chesney, Guillaume Jacquet, Ralf Steinberger, Jakub Piskorski
2017 Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)  
We also want to thank the IC1207 COST Action PARSEME and SIGLEX for their endorsement and support, as well as the EACL 2017 organizers.  ...  , and all involved participants for their interest in the workshop.  ...  In addition, we would like to thank Lauren Rudat for her suggestions on improving the stimuli, and to the anonymous reviewers for their suggestions on improving the paper.  ... 
doi:10.18653/v1/w17-1702 dblp:conf/mwe/ChesneyJSP17 fatcat:bv7aavgth5eurmzuphuowtuuhq

Why computers do not translate better

W. John Hutchins
1992 ASLIB Proceedings  
The linguistic and computational complexities of machine translation are not always apparent to all users or potential purchasers of systems.  ...  In this presentation I shall attempt to outline the difficulties encountered by computers in translating from one natural language into another.  ...  For the lay observer, it might seem that the most difficult area for MT must be the apparently unclassifiable variety of idiomatic constructions.  ... 
doi:10.1108/eb051296 fatcat:k6ww7msdb5cavcbe4cc7mx5cku

Toward a formal ontology for narrative

Desislava Zhekova, Robert Zangenfeind, Alena Mikhaylova, Tetiana Nikolaienko
2016 MatLit : Materialidades da Literatura  
The data set in use is the Russian novel Crime and Punishment by Fyodor Dostoyevsky and three German translations of it.  ...  This is a Java implementation that uses local grammars, ontological information, bilingual dictionaries and statistical approaches for alignment and search.  ...  Concerning syntactic constructions of Russian and German it is interesting, for example, to know how they alter when translated.  ... 
doi:10.14195/2182-8830_4-1_3 fatcat:zsluvycgbbg3foep3spzcxceve

Literal Occurrences of Multiword Expressions: Rare Birds That Cause a Stir

Agata Savary, Silvio Ricardo Cordeiro, Timm Lichte, Carlos Ramisch, Uxoa Iñurrieta, Voula Giouli
2019 Prague Bulletin of Mathematical Linguistics  
Multiword expressions can have both idiomatic and literal occurrences. For instance pulling strings can be understood either as making use of one's influence, or literally.  ...  : Basque, German, Greek, Polish and Portuguese.  ...  Acknowledgements This work was supported by the IC1207 PARSEME (PARSing and Multi-word Expressions) COST action 35 , by the French PARSEME-FR project (ANR-14-CERA-0001) 36  ... 
doi:10.2478/pralin-2019-0001 fatcat:no5aphmxgzhsdhe6i4lyajw3ni

The skill of natural interpreting in a trilingual child

Edita Hornáčková Klapicová
2021 Topics in Linguistics  
The present work seeks to contribute to the fields of translation and bilingual acquisition focusing on the particular case of natural translation/interpreting of a single Slovak/English/German balanced  ...  The third aim of the study is to document the types of errors produced by the child and through error analysis and statistical data reveal whether these errors may hinder the communication of accurate  ...  For instance, the light verb construction to be x years old contains the verb to be in English, the verb sein ('to be') in German but the verb mať ('to have') in Slovak and the verb tener ('to have') in  ... 
doi:10.2478/topling-2021-0004 fatcat:yrothhqbjnd4jdpazg2plddqpi
« Previous Showing results 1 — 15 out of 961 results