Multiword expressions at length and in depth
Extended papers from the MWE 2017 workshop
Stella Markantonatou, Carlos Ramisch, Agata Savary, Veronika Vincze (editors)
Cite as
.
2018.
Multiword expressions at length and in depth
: Extended papers from the MWE 2017 workshop.
(
2).
Berlin:
Language Science Press.
@book{2,
editor = {Markantonatou, Stella and Ramisch, Carlos and Savary, Agata and Vincze, Veronika },
title = {Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop},
year = {2018},
series = {},
number = {2},
address = {Berlin},
publisher = {Language Science Press}
}
Proofreaders
- Eitan Grossman
- Eleni Koutsomitopoulou
- Conor Pyle
- Felix Kopecky
- Ikmi Nur Oktavianti
- Jean Nitzke
- Melanie Röthlisberger
- Valeria Quochi
- Brett Reynolds
- Jeroen van de Weijer
- Steven Moran
- Harald Ulland
- Vadim Kimmelman
- Felix Hoberg
- Ivica Je?ud
- Trinka D'Cunha
- Ivelina Stoyanova
- Bojana (?or?evi?) Baaragin
About this book
The annual workshop on multiword expressions takes place since 2001 in conjunction with major computational linguistics conferences and attracts the attention of an ever-growing community working on a variety of languages, linguistic phenomena and related computational processing issues. MWE 2017 took place in Valencia, Spain, and represented a vibrant panorama of the current research landscape on the computational treatment of multiword expressions, featuring many high-quality submissions. Furthermore, MWE 2017 included the first shared task on multilingual identification of verbal multiword expressions. The shared task, with extended communal work, has developed important multilingual resources and mobilised several research groups in computational linguistics worldwide.
This book contains extended versions of selected papers from the workshop. Authors worked hard to include detailed explanations, broader and deeper analyses, and new exciting results, which were thoroughly reviewed by an internationally renowned committee. We hope that this distinctly joint effort will provide a meaningful and useful snapshot of the multilingual state of the art in multiword expressions modelling and processing, and will be a point point of reference for future work.
About Stella Markantonatou
Stella Markantonatou is a research director at Institute for Language and Speech Processing/Athena RIC, Athens, Greece. She holds a PhD in Linguistics from the University of Essex (UK). She has published on the formal study of the syntax-semantics interface, on phrase-based machine translation, and on the development of lexical resources. She has been a co-organiser of the MWE 2015, 2016 and 2017 workshops; currently she is a member of the standing committee of the SIGLEXMWE Section.
About Carlos Ramisch
Carlos Ramisch is an assistant professor and researcher at Aix Marseille University (France). He has a double PhD in computer science from the University of Grenoble (France) and from the Federal University of Rio Grande do Sul (Brazil). His research focuses on integrating multiword expressions processing into natural language processing models. He is interested in MWE discovery, representation and translation, lexical resources, computational semantics and machine learning. He co-chaired several editions of the MWE workshop from 2010 to 2018, co-edited a journal special issue on MWEs, co-organized the PARSEME shared task, developed the mwetoolkit, and co-authored several papers published at major conferences in computational linguistics, a survey and a book on MWEs.
About Agata Savary
Agata Savary is an associate professor in computer science at the University of Tours (France). She received her MSc degree in computer science from the University of Warsaw (Poland), and her PhD in computer science and applications from the ?University of Marne-la-Vallée (France). Her research interests include natural language processing, language resources and tools, multiword expressions, named entities, corpus annotation, computational morphology, finite state tools and XML processing. She served as the chair of the European IC1207 COST Action PARSEME (2013-2017) dedicated to parsing and multiword expressions. She co-chaired several editions of the MWE workshop and of the PARSEME shared task. She is currently the elected representative of the SIGLEX?-MWE Section and the co-editor-in-chief of the "Phraseology and Multiword Expressions" book? ?series? at? Language? Science? Press.
About Veronika Vincze
Veronika Vincze is a researcher and lecturer at the University of Szeged (Hungary). She has PhD degrees in linguistics and computer science, both from the University of Szeged. Her research interests include corpus building, information extraction, computational morphology and parsing, dependency syntax and multiword expressions. She has co-organized several national and international conferences (e.g. GWC2008, Szeged, Hungary, IWCLUL 2016, Szeged, Hungary) and she was a co-chair of the CoNLL-2010 Shared Task on Uncertainty Detection and the PARSEME Shared Tasks on Identifying Verbal Multiword Expressions.
Chapters
Exploiting multilingual lexical resources to predict MWE compositionality
Comparing bilingual word embeddings to translation dictionaries for extracting multilingual collocation equivalents
Identification of multiword expressions
Sequence models and lexical resources for MWE identification in French
Semi-automated resolution of inconsistency for a harmonized multiword-expression and dependency-parse annotation
Identifying verbal multiword expressions with POS tagging and parsing techniques
A transition-based verbal multiword expression analyzer
Semantic reranking of CRF label sequences for verbal multiword expression identification
Analysis and Insights from the PARSEME Shared Task dataset
PARSEME multilingual corpus of verbal multiword expressions
Identifying senses of particles in verb-particle constructions
Paraphrases of verbal multiword expressions
Spilling the bag on idiomatic variation
