Skip to main content.

Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)

Workshop at COLING 2018 (Santa Fe, USA), August 25-26, 2018

Organized and funded by the Special Interest Group for Annotation (SIGANN), the Special Interest Group on the Lexicon (SIGLEX), and the Special Interest Group on Computational Semantics (SIGSEM) of the Association for Computational Linguistics (ACL)

This joint event brings together:

Last updated: Aug 13, 2018

Proceedings

The LAW-MWE-CxG proceedings are available on the ACL Anthology.

Selected papers

34 papers (22 long and 12 short) were submitted to the research track of the workshop. 16 long papers and 6 short ones were selected, and 1 paper was withdrawn. The overall selectivity rate is 65%.
8 system description papers were submitted to the shared task track. All were selected. The reviewing modalities were different in this track, therefore we do not count these papers in the workshop selectivity rate.

Program

Saturday, August 25, 2018 (Peralta room)

8:55–09:00Opening
 Session 1: Multiword expressions (chair: Carlos Ramisch)
09:00–10:00 Invited talk: Leaving no token behind: comprehensive (and delicious) annotation of MWEs and supersenses
Nathan Schneider
10:00–10:30 Poster boosters of research papers (2 min. per poster)
10:30–11:00COFFEE BREAK
 Session 2: Multiword expressions (chair: Tim Baldwin)
11:00–11:30Fixed Similes: Measuring aspects of the relation between MWE idiomatic semantics and syntactic flexibility
Stella Markantonatou, Panagiotis Kouris and Yanis Maistros
11:30–12:00Edition 1.1 of the PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions
Carlos Ramisch, Silvio Ricardo Cordeiro, Agata Savary, Veronika Vincze, Verginica Barbu Mititelu, Archna Bhatia, Maja Buljan, Marie Candito, Polona Gantar, Voula Giouli, Tunga Güngör, Abdelati Hawwari, Uxoa Iñurrieta, Jolanta Kovalevskaitė, Simon Krek, Timm Lichte, Chaya Liebeskind, Johanna Monti, Carla Parra Escartín, Behrang QasemiZadeh, Renata Ramisch, Nathan Schneider, Ivelina Stoyanova, Ashwini Vaidya and Abigail Walsh
12:00–12:10TRAVERSAL at PARSEME Shared Task 2018: Identification of Verbal Multiword Expression using a Discriminative Tree-Structured Model
Jakub Waszczuk
12:10–12:20TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions
Regina Stodden, Behrang QasemiZadeh and Laura Kallmeyer
12:20–12:30Poster boosters of 6 other shared task papers (2 min. per poster)
12:30–13:50LUNCH BREAK
13:50–15:50Session 3: Posters (chair: Stella Markantonatou; 7 research papers, 4 system papers)
 The RST Spanish-Chinese Treebank
Shuyuan Cao, Iria da Cunha and Mikel Iruskieta
 The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses
Hessel Haagsma, Malvina Nissim and Johan Bos
 Fine-grained termhood prediction for German compound terms using neural networks
Anna Hätty and Sabine Schulte im Walde
 Verbal Multiword Expressions in Basque corpora
Uxoa Iñurrieta, Itziar Aduriz, Ainara Estarrona, Itziar Gonzalez-Dios, Antton Gurrutxaga, Ruben Urizar and Iñaki Alegria
 Towards a Computational Lexicon for Moroccan Darija: Words, Idioms, and Constructions
Jamal Laoudi, Claire Bonial, Lucia Donatelli, Stephen Tratz and Clare Voss
 Cooperating Tools for MWE Lexicon Management and Corpus Annotation
Yuji Matsumoto, Akihiko Kato, Hiroyuki Shindo and Toshio Morita
 Developing and Evaluating Annotation Procedures for Twitter Data during Hazard Events
Kevin Stowe, Martha Palmer, Jennings Anderson, Marina Kogan, Leysia Palen, Kenneth M. Anderson, Rebecca Morss, Julie Demuth and Heather Lazrus
 CRF-Seq and CRF-DepTree at PARSEME Shared Task 2018: Detecting Verbal MWEs using Sequential and Dependency-based Approaches
Erwan Moreau, Ashjan Alsulaimani, Alfredo Maldonado and Carl Vogel
 Mumpitz at PARSEME Shared Task 2018: A Bidirectional LSTM for the Identification of Verbal Multiword Expressions
Rafael Ehren, Timm Lichte and Younes Samih
 TRAVERSAL at PARSEME Shared Task 2018: Identification of Verbal Multiword Expression using a Discriminative Tree-Structured Model
Jakub Waszczuk
 Veyn at PARSEME Shared Task 2018: Recurrent neural networks for VMWE identification
Nicolas Zampieri, Manon Scholivet, Carlos Ramisch and Benoit Favre
15:50–16:20COFFEE BREAK
16:20–18:00Session 4: Posters (chair: Stella Markantonatou; 6 research papers, 4 system papers)
 "Fingers in the Nose": Evaluating Speakers’ identification of Multi-Word Expressions Using a Slightly Gamified Crowdsourcing Platform
Karën Fort, Bruno Guillaume, Matthieu Constant, Nicolas Lefèbvre and Yann-Alan Pilatte
 Do Character-level Neural Network Language Models Capture Knowledge of Multiword Expression Compositionality?
Ali Hakimi Parizi and Paul Cook
 A Treebank for the Healthcare Domain
Nganthoibi Oinam, Diwakar Mishra, Pinal Patel, Narayan Choudhary and Hitesh Desai
 All Roads Lead to UD: Converting Stanford and Penn Parses to English Universal Dependencies with Multilayer Annotations
Siyao Peng and Amir Zeldes
 Constructing an Annotated Corpus of Verbal MWEs for English
Abigail Walsh, Claire Bonial, Kristina Geeraert, John P. McCrae, Nathan Schneider and Clarissa Somers
 A syntax-based scheme for the annotation and segmentation of German spoken language interactions
Swantje Westpfahl and Jan Gorisch
 Deep-BGT at PARSEME Shared Task 2018: Bidirectional LSTM-CRF Model for Verbal Multiword Expression Identification
Gözde Berk, Berna Erden and Tunga Güngör
 GBD-NER at PARSEME Shared Task 2018: Multi-word Expression Detection using Bidirectional Long-Short-Term Memory Networks and graph-based decoding
Tiberiu Boroș and Ruxandra Burtica
 TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions
Regina Stodden, Behrang QasemiZadeh and Laura Kallmeyer
 VarIDE at PARSEME Shared Task 2018: Are variants really as alike as two peas in a pod?
Caroline Pasquer, Carlos Ramisch, Agata Savary and Jean-Yves Antoine

Sunday, August 26, 2018 (Peralta room)

 Session 5: Constructions (chair: Nathan Schneider)
09:00–10:00 Invited talk: Annotation Schemes for Surface Construction Labeling
Lori Levin
10:00–10:30The Interplay of Form and Meaning in Complex Medical Terms: Evidence from a Clinical Corpus
Leonie Grön, Ann Bertels and Heylen Kris
10:30–11:00COFFEE BREAK
 Session 6: Constructions (chair: Amir Zeldes)
12:00–12:30Processing MWEs: Neurocognitive Bases of Verbal MWEs and Lexical Cohesiveness within MWEs
Shohini Bhattasali, Murielle Fabre and John Hale
11:30–12:00Discourse and lexicons: lexemes, MWEs, grammatical constructions and compositional word combinations to signal discourse relations
Laurence Danlos
11:00–11:30From Chinese word segmentation to extraction of constructions: two sides of the same algorithmic coin
Jean-Pierre Colson
12:30–13:50LUNCH BREAK
 Session 7: Linguistic annotation (chair: Agata Savary)
13:50–14:50 Invited talk: From Lexical Functional Grammar to Enhanced Universal Dependencies
Adam Przepiórkowski
14:50–15:20Annotation of Tense and Aspect Semantics for Sentential AMR
Lucia Donatelli, Michael Regan, William Croft and Nathan Schneider
15:20–15:50An Annotated Corpus of Picture Stories Retold by Language Learners
Christine Köhn and Arne Köhn
15:50–16:20COFFEE BREAK
 Session 8: Linguistic annotation (chair: Josef Ruppenhofer)
16:20–16:40Improving Domain Independent Question Parsing with Synthetic Treebanks
Halim-Antoine Boukaram, Nizar Habash, Micheline Ziadee and Majd Sakr
16:40–17:40Business meeting [slides] [minutes] [MWE research issues]

Session 1: Poster boosters in the research track

  1. THE RST SPANISH-CHINESE TREEBANK
    Shuyuan Cao, Iria da Cunha and Mikel Iruskieta
  2. A TREEBANK FOR THE HEALTHCARE DOMAIN
    Nganthoibi Oinam, Diwakar Mishra, Pinal Patel, Narayan Choudhary and Hitesh Desai
  3. TOWARDS A COMPUTATIONAL LEXICON FOR MOROCCAN DARIJA: WORDS, IDIOMS, AND CONSTRUCTIONS
    Jamal Laoudi, Claire Bonial, Lucia Donatelli, Stephen Tratz and Clare Voss
  4. A SYNTAX-BASED SCHEME FOR THE ANNOTATION AND SEGMENTATION OF GERMAN SPOKEN LANGUAGE INTERACTIONS
    Swantje Westpfahl and Jan Gorisch
  5. ALL ROADS LEAD TO UD: CONVERTING STANFORD AND PENN PARSES TO ENGLISH UNIVERSAL DEPENDENCIES WITH MULTILAYER ANNOTATIONS
    Siyao Peng and Amir Zeldes
  6. COOPERATING TOOLS FOR MWE LEXICON MANAGEMENT AND CORPUS ANNOTATION
    Yuji Matsumoto, Akihiko Kato, Hiroyuki Shindo and Toshio Morita
  7. DEVELOPING AND EVALUATING ANNOTATION PROCEDURES FOR TWITTER DATA DURING HAZARD EVENTS
    Kevin Stowe, Martha Palmer, Leysia Palen, Kenneth M. Anderson, Jennings Anderson, Marina Kogan, Rebecca Morss, Julie Demuth and Heather Lazrus
  8. "FINGERS IN THE NOSE": EVALUATING THE SPEAKERS’ IDENTIFICATION OF MWES USING A SLIGHTLY GAMIFIED CROWDSOURCING PLATFORM
    Karën Fort, Bruno Guillaume, Matthieu Constant, Nicolas Lefèbvre and Yann-Alan Pilatte
  9. VERBAL MULTIWORD EXPRESSIONS IN BASQUE CORPORA
    Uxoa Iñurrieta, Itziar Aduriz, Ainara Estarrona, Itziar Gonzalez-Dios, Antton Gurrutxaga and Ruben Urizar
  10. CONSTRUCTING AN ANNOTATED CORPUS OF VERBAL MWES FOR ENGLISH
    Abigail Walsh and Claire Bonial
  11. THE OTHER SIDE OF THE COIN: UNSUPERVISED DISAMBIGUATION OF POTENTIALLY IDIOMATIC EXPRESSIONS BY CONTRASTING SENSES
    Hessel Haagsma, Malvina Nissim and Johan Bos
  12. DO CHARACTER-LEVEL NEURAL NETWORK LANGUAGE MODELS CAPTURE KNOWLEDGE OF MULTIWORD EXPRESSION COMPOSITIONALITY?
    Ali Hakimi Parizi and Paul Cook
  13. FINE-GRAINED TERMHOOD PREDICTION FOR GERMAN COMPOUND TERMS USING NEURAL NETWORKS
    Anna Hätty and Sabine Schulte im Walde

Session 2: Poster boosters in the shared task track

  1. DEEP-BGT AT PARSEME SHARED TASK 2018: BIDIRECTIONAL LSTM-CRF MODEL FOR VERBAL MULTIWORD EXPRESSION IDENTIFICATION
    Gözde Berk, Berna Erden and Tunga Gungor
  2. GBD-NER AT PARSEME SHARED TASK 2018: MULTI-WORD EXPRESSION DETECTION USING BIDIRECTIONAL LONG-SHORT-TERM MEMORY NETWORKS AND GRAPH-BASED DECODING
    Tiberiu Boroș and Ruxandra Burtica
  3. MUMPITZ AT PARSEME SHARED TASK 2018: A BIDIRECTIONAL LSTM FOR THE IDENTIFICATION OF VERBAL MULTIWORD EXPRESSIONS
    Rafael Ehren, Timm Lichte and Younes Samih
  4. CRF-SEQ and CRF-DEPTREE AT PARSEME SHARED TASK 2018:: DETECTING VERBAL MWEs USING SEQUENTIAL AND DEPENDENCY-BASED APPROACHES
    Erwan Moreau, Ashjan Alsulaimani, Alfredo Maldonado and Carl Vogel
  5. VARIDE AT PARSEME SHARED TASK 2018: ARE VARIANTS REALLY AS ALIKE AS TWO PEAS IN A POD?
    Caroline Pasquer, Agata Savary, Carlos Ramisch and Jean-Yves Antoine
  6. VEYN AT PARSEME SHARED TASK 2018: RECURRENT NEURAL NETWORKS FOR VMWE IDENTIFICATION
    Nicolas Zampieri, Manon Scholivet, Carlos Ramisch and Benoit Favre