long papers (30 mins)
short papers (15 mins)
project reports (10 mins)
demonstrations (20 mins)
posters
Long papers should be limited to 8 pages;
Demonstration papers must be at most 5 pages text and can have additional 3 pages screen dumps or images;
Short papers, project descriptions and posters should be limited to 5 pages.
Papers need to be submitted to the EasyChair website.
The format of the paper is the ACL format (PDF)
The conference program will include oral presentations and demonstration sessions with sufficient time for discussions of the issues raised.
The deadline for submissions is September 6, 2015. Decisions regarding acceptance will be announced to the authors on October 18, 2015. Final papers are due on October 31, 2015.
Beneficiary: Institutul de Cercetari pentru Inteligenta Artificiala
“Mihai Draganescu” (ICIA)
Calea 13 Septembrie nr 13, sector 5, Bucuresti, cod 050711, Romania
Bank : BRD Unirea
Bdul Vintila Voda Nr 2 Bloc E1 Sector 3 Cod postal 60396 Bucharest
Swift code : BRDEROBU
IBAN: RO93BRDE441SV46786704410
Identity code: 6121265
Amount representing: GWC 2016 conference fee for...... (name of participant)
Those participants needing an invoice for the payment will contact Verginica Mititelu (see email address on the OC page) providing the following information:
Name/Institution
Address
VAT number
Account number
Bank
8:00-8:45 Registration of participants
8:45-9:00 Opening
9:00-11:00 Workshop on the Collaborative Interlingual Index (part I)
• Piek Vossen, Francis Bond and John P. McCrae, Toward a truly multilingual Global Wordnet Grid.
• Francis Bond, John P. McCrae, Adding a wordnet to the GWG: adding concepts to the ILI (part I)
11:00-11:20 coffee break
11:20-13:20 Workshop on the Collaborative Interlingual Index (part II)
• Francis Bond, John P. McCrae, Adding a wordnet to the GWG: adding concepts to the ILI (part II)
• Christiane Fellbaum, How and when to add a new concept and how to define it
13:20-14:30 lunch break
14:30-16:30 Session 1
• 14:30-15:00 Maciej Piasecki, Stan Szpakowicz, Marek Maziarz and Ewa Rudnicka, plWordNet 3.0 -- Almost There
• 15:00-15:30 Mehrnoush Shamsfard and Yasaman Ghazanfari, Augmenting FarsNet with New Relations and Structures for verbs
• 15:30-16:00 Yasser Regragui, Lahsen Abouenour, Fettoum Krieche, Karim Bouzoubaa and Paolo Rosso, Arabic WordNet: New Content and New Applications
16:30-16:50 coffee break
16:50 – 18:50 Session 2
• 17:50-18:20 Qingqing Cai, James Gung, Maochen Guan, Gerald Kurlandski and Adam Pease, Word Substitution in Short Answer Extraction: A WordNet-based Approach
9:00-10:00 Invited talk: Erhard Hinrichs, The Awful German Language: How to cope with the Semantics of Nominal Compounds in GermaNet and in Natural Language Processing
10:00-10:30 Special session: Jon French, Oxford Global Languages - an introduction
10:30-10:45 poster teaser session
10:45-12:00 Poster session and coffee:
• Stanley Madonsela, Mampaka Lydia Mojapelo, Rose Masubelele and James Mafela, African WordNet: A Viable Tool for Sense Discrimination in the Indigenous African Languages of South Africa
• Ahti Lohk, Christiane Fellbaum and Leo Vohandu, Tuning Hierarchies in Princeton WordNet
• Harpreet Singh Arora, Sudha Bhingardive and Pushpak Bhattacharyya, Unsupervised Approach to Detect Most Frequent Sense of a Word Using BabelNet
• Apurva Nagvenkar, Jyoti Pawar and Pushpak Bhattacharyya, IndoWordNet Conversion to Web Ontology Language (OWL)
16:00-19:00 Session 3
• 17:30-18:00 Maciej Piasecki, Paweł Kędzia and Marlena Orlińska, plWordNet in Word Sense Disambiguation task
9:00-11:00 Session 4
• 9:30-9:45 Sven Aller, Heili Orav, Kadri Vare and Sirli Zupping, Playing Alias - efficiency for wordnet(s)
• 9:45-10:00 Monica Berti, Yuri Bizzoni, Federico Boschetti, Gregory R. Crane, Riccardo Del Gratta and Tariq Yousef, Ancient Greek WordNet Meets the Dynamic Lexicon: the Example of the Fragments of the Greek Historians
• 10:00-10:15 Agnieszka Dziob and Michał Wendelberger, Extraction and description of multi-word lexical units in plWordNet 3.0
• 10:15-10:30 Emiel van Miltenburg, WordNet-based similarity metrics for adjectives
• 10:30-10:45 Sudha Bhingardive, Prateek Sappadla and Pushpak Bhattacharyya, IndoWordNet::Similarity - a tool for measuring the Semantic Similarity and Relatedness for Indian Languages
• 10:45-11:00 Diptesh Kanojia, Shehzaad Dhuliawala and Pushpak Bhattacharyya, A picture is worth a thousand words: Using OpenClipArt library for enriching IndoWordNet
11:00-11:20 coffee break
11:20-13:15 Session 5
• 11:20-11:35 Csilla Horváth, Ágoston Nagy, Norbert Szilágyi and Veronika Vincze, Where Bears Have the Eyes of Currant: Towards a Mansi WordNet
• 11:35-11:50 Thai Phuong Nguyen, Van-Lam Pham, Hoang-An Nguyen, Huy-Hien Vu, Ngoc-Anh Tran, Thi-Thu-Ha Truong, A Two-Phase Approach for Building Vietnamese Wordnet
• 11:50-12:20 Adam Rambousek and Ales Horak, DEBVisDic: instant wordnet building
• 12:20-12:40 Borislav Rizov and Tsvetana Dimitrova, Hydra for Web: A Browser for Easy Access to Wordnets
• 12:40-13:00 Diptesh Kanojia, Raj Dabre and Pushpak Bhattacharyya, Sophisticated Lexical Databases - Simplified Usage: Mobile Applications and Browser Plugins For Wordnets
13:00-14:30 lunch break
14:30-16:30 Session 6
• 14:30-15:00 Tanuja Ajotikar and Malhar Kulkarni, Adverbs in Sanskrit Wordnet
• 15:00-15:30 Marek Maziarz, Stan Szpakowicz and Michal Kalinski, Adverbs in plWordNet: Theory and Implementation
• 15:30-16:00 Amanda Hicks, Michael Rutherford, Christiane Fellbaum and Jiang Bian, An Analysis of WordNet’s Coverage of Gender Identity Using Twitter and The National Transgender Discrimination Survey
• 16:00-16:30 Meghna Singh, Rajita Shukla, Jaya Saraswati, Laxmi Kashyap, Diptesh Kanojia and Pushpak Bhattacharyya, Mapping it differently: A solution to the linking challenges
16:30-16:50 coffee break
16:50-18:50 Session 7
• 17:20-17:50 Nasim Fakoornia and Negar Davari Ardakani, Establishing Morpho-semantic Relations in FarsNet: A Focus on Derived Nouns
9:00-11:00 Session 8
• 9:00-9:30 Mampaka Lydia Mojapelo, Semantics of body parts in African WordNet: a case of Northern Sotho
• 9:30-10:00 Raksha Sharma and Pushpak Bhattacharyya, High, Medium or Low? Detecting Intensity Variation Among polar synonyms in WordNet
• 10:30-11:00 Ewa Rudnicka, Wojciech Witkowski and Łukasz Grabowski, Towards a methodology for filtering out gaps and mismatches across wordnets: the case of plWordNet and Princeton WordNet
11:00-11:20 coffee break
11:20-13:20 Session 9
• 11:20-11:35 Tommaso Petrolito, A language-independent LESK based approach to Word Sense Disambiguation
• 11:50-12:20 Marijn Schraagen, Folktale similarity based on ontological abstraction
• 12:50-13:20 Dhirendra Singh, Sudha Bhingardive and Pushpak Bhattacharyyaa, Detection of Compound Nouns and Light Verb Constructions using IndoWordNet
13:20-14:30 lunch break
14:30-16:30 Session 10
• 15:30-16:00 Michael Zock and Didier Schwab, WordNet and beyond : the case of lexical access
• 16:00-16:30 Bill Huang, WNSpell: a WordNet-Based Spell Corrector
16:30-16:50 coffee break
16:50-18:50 Session 11
18:50 Closing
19:00 Cocktail at the Romanian Academy Library, ground floor
13:30 Visit of the House of People (Palace of Parliament)
20:00 Gala Dinner at Caru’ cu bere restaurant
The Awful German Language: How to cope with the Semantics of Nominal Compounds
in GermaNet and in Natural Language Processing
The title for my presentation borrows from Mark Twain's well-known 1880 essay "The Awful German Language", where Twain cites pervasive nominal compounding in German as one of the pieces of evidence for the "awfulness" of the language. Two much cited examples of noun compounds that are included in the Duden dictionary of German are Kraftfahrzeughaftpflichtversicherung (‘motor car liability insurance’) and Donaudampfschifffahrtsgesellschaft (‘Danube steamboat shipping company’). Any dictionary of German, including the German word net GermaNet, has to offer an account of such compound words. Currently, GermaNet contains more than 55,000 nominal compounds. As the coverage of nouns in GermaNet is extended, new noun entries are almost always compounds.
In this talk I will present an account of how to model nominal compounds in GermaNet with particular focus on the semantic relations that hold between the constituents of a compound, e.g., the WHOLE-PART relation in the case of Roboterarm ('robot arm') or the LOCATION relation in the case of Berghütte ('mountain hut'). This account, developed jointly with Reinhild Barkey, Corina Dima, Verena Henrich, Christina Hoppermann, and Heike Telljohann, borrows heavily from previous research on semantic relations in theoretical linguistics, psycholinguistics, and computational linguistics.
The second part of the talk will focus on using the semantic modelling of nominal compounds in a word net for the automatic classification of semantic relations for (novel) compound words. Here, I will present the results of recent collaborative work with Corina Dima and Daniil Sorokin, using machine learning techniques such as support vector machines as well as deep neural network classifiers and a variety of publicly available word-embeddings, which have been developed in the framework of distributional semantics.
Erhard Hinrichs is professor of Computational Linguistics and director of the Computational Linguistics research group at the University of Tübingen, Germany. He obtained a PhD in Linguistics from the Ohio State University in 1985. His previous positions include Research Fellow, Beckman Institute for Advanced Science and Technology and Assistant Professor, University of Illinois, Urbana-Champaign; Research Scientist, Artificial Intelligence Department, Bolt Beranek and Newman Laboratories, Cambridge. He has also held positions as a Visiting Professor at the University of the Saarland, Saarbrücken, Stockholm University, NTT Laboratories, Yokosuka, Japan, The Ohio State University, and the European Academy of Bozen/Bolzano. He has been a principal investigator in the collaborative research centers “Theoretical Foundations of Computational Linguistics” (SFB 340; 1992-2000), “Linguistic Data Structures” (SFB 441; 1999-2008), and “Emergence of Meaning” (SFB 833; since 2009), all at the University of Tübingen.
His research interests include the computational modelling of language comprehension (particularly of syntax and semantics) and of language variation with special emphasis on the use of machine learning approaches. Dr. Hinrichs has been the project leader for the development of GermaNet, the wordnet for German, which has been under development in his research group at the University of Tübingen since 1995.