The conference will be divided into two oral sessions, one in the morning and one in the afternoon, each of them beginning with an invited talk. The lunch will be accompanied by a poster session, which will feature accepted papers and a Language Technologies Exhibition.
Prof. Eric Laporte, Universite Paris-Est Marne-la-Vallee (morning talk)
Eric Laporte is a professor in Computer Science (with a specialization in language technology) at Universit? Paris-Est Marne-la-Vall?e. He is interested in natural language processing, language resources, natural language parsing, corpus processing systems, lexical analysis, information extraction. More specifically, his recent work examines hybrid parsing and semantic disambiguation, inflectional morphology of Arabic and Malagasy, and syntax-based taxonomy of French verbs and adjectives. His pedagogical interests also include computer theory and software development.
He holds a PhD and a post-doctoral degree from the University of Paris 7, a MSc in computer theory and a B.A. in linguistics. Eric Laporte has published in Language Sciences, in Cambridge University Press and MIT Press books, and in the ACL and RANLP conferences.
Recently, he participated in the GramLab (accessible recognition, extraction and correction tools) and DoXa (opinion mining) projects. He coordinates the net of users of the Unitex-GramLab system. He has supervised 20 PhDs. He is an editor of the Lingvisticae Investigationes journal.
Interaction between Linguists and Machine Learning (abstract of the talk)
When we design hybrid systems which combine machine-learning algorithms with symbolic language resources elaborated by linguists, we divide tasks between linguists and algorithms, and we select models that facilitate this division of tasks.
What are the challenges faced by linguists and by machine learning algorithms in this context?
What are the assets that allow them to take on these challenges?
Is the problem different for different types of resources?
Which trends in linguistics equip linguists best for building resources?
Prof. Cvetana Krstev, University of Belgrade (afternoon talk)
Dr. Cvetana Krstev is a full-time professor at the University of Belgrade. After graduating from the University of Belgrade, Dr. Krstev worked as a computer specialist at the Institute for Mathematics at the Serbian Academy of Sciences and Art. She became a staff member of the University in 1985, obtained her PhD in Computer Science in 1997 and became full-time professor in 2014. Her professional activities, besides teaching at undergraduate, graduate and doctoral levels, are mainly within the University of Belgrade HLT Group.
Professor Krstev published one book and more than 130 scientific papers most of them related to natural language processing, mainly language resource development and their application. She has developed the Serbian morphological e-dictionary (with Dusko Vitas) and is one of the key contributors to the development of Serbian WordNet, the Corpus of Contemporary Serbian, the parallel Serbian/English corpus, and many other language resources and tools. She participated in several other international and national language related projects. She served as a member of program committees of many international conferences and workshops in the domain of computational linguistics and languages resources. She is the editor-in-chief of the journal for Information Sciences InfoTheca.
Developing Resources for the Culinary Domain. (abstract of the talk)
The talk presents three lexical resources for Serbian used in the development of NLP-based applications in the culinary domain. Two of them – the Serbian WordNet and morphological e-dictionaries – have already been in development, while the third one – a corpus of culinary recipes – has been designed specifically for this purpose. The author presents the use of each of these resources to correct and enlarge the other two. Particular attention is given to the enrichment of morphological dictionaries and WordNet with approximate measure terminology and the development of an approximate measure ontology, the first step in the development of the comprehensive ontology of the culinary domain.
8:30 – 9:00 Registration
9:00 – 9:15 Opening – Prof. Svetla Koeva
9:15 – 10:00 Invited Talk – Prof. Eric Laporte. Interaction between Linguists and Machine Learning.
10:00 – 12:30 MORNING SESSION
10:00 – 10:30 Ivan Derzhanski and Rositsa Dekova. Electronic Language Resources in Teaching Mathematical Linguistics.
10:30 – 11:00 Diman Karagiozov. Harnessing Language Technologies in Multilingual Information Channelling Services.
11:00 – 11:30 COFFEE BREAK / PRESS CONFERENCE
11:30 – 12:00 Svetlozara Leseva, Ivelina Stoyanova, Borislav Rizov, Maria Todorova and Ekaterina Tarpomanova. Automatic Semantic Filtering of Morphosemantic Relations in WordNet.
12:00 – 12:30 Ekaterina Tarpomanova, Svetlozara Leseva, Maria Todorova, Tsvetana Dimitrova, Borislav Rizov, Verginica Barbu Mititelu and Elena Irimia. Noun-Verb Derivation in the Bulgarian and the Romanian WordNet – A Comparative Approach.
12:30 – 14:15 LUNCH BREAK + POSTER SESSION + LANGUAGE TECHNOLOGIES EXHIBITION
14:15 – 15:00 Invited Talk – Prof. Cvetana Krstev. Developing Resources for the Culinary Domain.
15:00 – 17:30 – AFTERNOON SESSION
15:00 – 15:30 Daniela Majchrakova, Ondrej Dusek, Jan Hajic, Agata Karcova and Radovan Garabik. Semi-Automatic Detection of Multiword Expressions in the Slovak Dependency Treebank.
15:30 – 16:00 Ivelina Stoyanova. Automatic Categorisation of Multiword Expressions and Named Entities in Bulgarian.
16:00 – 16:30 COFFEE BREAK
16:30 – 17:00 Ivan Derzhanski and Olena Siruk. Temporal Adverbs and Adverbial Expressions in a Corpus of Bulgarian and Ukrainian Parallel Texts.
17:00 – 17:30 Tsvetana Dimitrova and Andrej Boyadzhiev. Historical Corpora of Bulgarian Language and Second Position Markers.
Luchezar Jackov. Mаchine Translation Based on WordNet and Dependency Relations.
Sebastiao Pais, Gael Dias and Rumen Moraliyski. Recognize the Generality Relation between Sentences Using Asymmetric Association Measures.
Sebastiao Pais, Gael Dias, Joao Cordeiro and Rumen Moraliyski. Unsupervised and Language Independent Method to Recognize Textual Entailment by Generality.
LANGUAGE TECHNOLOGIES EXHIBITION
Kjetil Ra Hauge, Yovka Tisheva, Marina Dzhonova and Atanas Atanasov (University of Oslo, Sofia University). BgSpeech – a Resource for Spoken Bulgarian.
Mariana Damova (Mozaika Ltd.). Mozaika – the Humanizing Technologies Lab.
Mariana Damova (Bulgariana). Bulgariana, the Bulgarian Version of Europeana.
Anelia Belogay, Elitsa Marinova (Tetracom Interactive Solutions). Harnessing Linguistic Technologies.
Galya Todorova, Argir Todorov (Datecs GIS Center). Intelligent Search in Bgmaps.com.
Dilyana Krushkova (Kodar). OpenBook. An Online Tool for People with Autism to Simplify Text.
Stoyan Vellev (SAP Labs Bulgaria). The Linguistic Capabilities of SAP HANA: Full-text Search, Fuzzy Search, Sentiment Analysis.