Influence of Treebank Design on Representation of Multiword Expressions

Bejček, Eduard; Straňák, Pavel; Zeman, Daniel

doi:10.1007/978-3-642-19400-9_1

Cited by 2 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Continuous MWEs such as compound nouns, adverbs and prepositions and conjunctions are covered in some treebanks as in (Abeillé et al, 2003;Branco et al, 2010). Verbal MWEs (VMWEs) have been addressed for a fewer number of languages (Bejček et al, 2011;Eryigit et al, 2015;Seraji et al, 2014), and often restricted to some subtypes only, e.g., light-verb constructions (Vincze and Csirik, 2010).…”

Section: Introductionmentioning

confidence: 99%

Projecting Multiword Expression Resources on a Polish Treebank

Savary¹,

Waszczuk²

2017

Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing

View full text Add to dashboard Cite

Multiword expressions (MWEs) are linguistic objects containing two or more words and showing idiosyncratic behavior at different levels. Treebanks with annotated MWEs enable studies of such properties, as well as training and evaluation of MWE-aware parsers. However, few treebanks contain full-fledged MWE annotations. We show how this gap can be bridged in Polish by projecting 3 MWE resources on a constituency treebank.

show abstract

Section: Introductionmentioning

confidence: 99%

Projecting Multiword Expression Resources on a Polish Treebank

Savary¹,

Waszczuk²

2017

Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing

View full text Add to dashboard Cite

show abstract

**Bridging the “gApp”: improving neural machine translation systems for multiword expression detection**

Hidalgo-Ternero

Pastor

2020

Yearbook of Phraseology

View full text Add to dashboard Cite

The present research introduces the tool gApp, a Python-based text preprocessing system for the automatic identification and conversion of discontinuous multiword expressions (MWEs) into their continuous form in order to enhance neural machine translation (NMT). To this end, an experiment with semi-fixed verb–noun idiomatic combinations (VNICs) will be carried out in order to evaluate to what extent gApp can optimise the performance of the two main free open-source NMT systems —Google Translate and DeepL— under the challenge of MWE discontinuity in the Spanish into English directionality. In the light of our promising results, the study concludes with suggestions on how to further optimise MWE-aware NMT systems.

show abstract

Influence of Treebank Design on Representation of Multiword Expressions

Cited by 2 publications

References 6 publications

Projecting Multiword Expression Resources on a Polish Treebank

Projecting Multiword Expression Resources on a Polish Treebank

**Bridging the “gApp”: improving neural machine translation systems for multiword expression detection**

Contact Info

Product

Resources

About