Download Proceedings

Program

Preliminary program, to be confirmed

    9:00-- 9:20
    Opening Remarks
    Invited Talk:
    9:20--10:20
    Slavic Information Extraction and Partial Parsing Przepiórkowski Adam
    Session 1: Information Extraction
    10:20--10:45
    Implementation of Croatian NERC System Bekavac Božo, Tadić Marko
    10:45--11:15
    Morning Cofee Break
    11:15--11:40
    A Language Independent Approach for Name Categorization and Discrimination Kozareva Zornitsa, Vázquez Sonia, Montoyo Andrés
    11:40--12:05
    Lemmatization of Polish Person Names Piskorski Jakub, Sydow Marcin, Kupsc Anna
    12:05--12:30
    Automatic Processing of Diabetic Patients' Hospital Documentation Marciniak Malgorzata, Mykowiecka Agnieszka
    12:30--14:30
    Lunch
    Session 2: Information Extraction and Enabling Technologies
    14:30--14:55
    Towards the Automatic Extraction of Definitions in Slavic Przepiórkowski Adam, Degórski Łukasz, Spousta Miroslav, Simov Kiril, Osenova Petya, Lemnitzer Lothar, Kuboň Vladislav, Wójtowicz Beata
    14:55--15:20
    Unsupervised Methods of Topical Text Segmentation for Polish Flejter Dominik, Wieloch Karol, Abramowicz Witold
    15:20--15:45
    Multi-word Term Extraction for Bulgarian Koeva Svetla
    15:45--16:15
    Afternoon Break
    Session 3: Enabling Technologies
    16:15--16:40
    The Best of Two Worlds: Cooperation of Statistical and Rule-Based Taggers for Czech Spoustová Drahomíra "johanka", Hajič Jan, Votrubec Jan, Krbec Pavel, Květoň Pavel
    16:40--17:05
    Derivational Relations in Czech WordNet Pala Karel, Hlaváčková Dana
    Session 4: Poster Session
    17:05--18:00
    Multilingual Word Sense Discrimination: A Comparative Cross-Linguistic Study Rozovskaya Alla, Sproat Richard
    17:05--18:00
    Named Entity Recognition for Ukrainian: A Resource-Light Approach Katrenko Sophia, Adriaans Pieter
    17:05--18:00
    Morphological Annotation of the Lithuanian Corpus Rimkutė Erika, Daudaravičius Vidas, Utka Andrius

Invited Speaker

Adam Przepiórkowski from the Polish Academy of Sciences.

    Slavic IE and Partial Parsing

    Abstract

    Information Extraction (IE) often involves some amount of partial syntactic processing. This is clear in cases of interesting highlevel IE tasks, such as finding information about who did what to whom (when, where, how and why), but it is also true in case of simpler IE tasks, such as finding company names in texts. The aim of this paper is to give an overview of Slavonic phenomena which pose particular problems for IE and partial parsing, and some phenomena which seem easier to treat in Slavonic than in Germanic or Romance; I also mention various tools which have been used for the partial processing of Slavonic.

Site Meter