@inproceedings{BelicaKeibelKupietzetal.2010,
  author    = {Belica, Cyril and Keibel, Holger and Kupietz, Marc and Perkuhn, Rainer and Vachkov{\´a}, Marie},
  title     = {Putting corpora into perspective. Rethinking synchronicity in corpus linguistics},
  series = {Proceedings of the Corpus Linguistics Converence 2009},
  editor    = {Mahlberg, Michaela and Gonz{\´a}lez-D{\´i}az, Victorina and Smith, Catherine},
  publisher = {University of Liverpool},
  address   = {Liverpool},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47393},
  pages     = {22},
  year      = {2010},
  abstract  = {Empirical synchronic language studies generally seek to investigate language phenomena for one point in time, even though this point in time is often not stated explicitly. Until today, surprisingly little research has addressed the implications of this time-dependency of synchronic research on the composition and analysis of data that are suitable for conducting such studies. Existing solutions and practices tend to be too general to meet the needs of all kinds of research questions. In this theoretical paper that is targeted at both corpus creators and corpus users, we propose to take a decidedly synchronic perspective on the relevant language data. Such a perspective may be realised either in terms of sampling criteria or in terms of analytical methods applied to the data. As a general approach for both realisations, we introduce and explore the FReD strategy (Frequency Relevance Decay) which models the relevance of language events from a synchronic perspective. This general strategy represents a whole family of synchronic perspectives that may be customised to meet the requirements imposed by the specific research questions and language domain under investigation.},
  language  = {en}
}
@incollection{BelicaKeibelKupietzetal.2010,
  author    = {Belica, Cyril and Keibel, Holger and Kupietz, Marc and Perkuhn, Rainer},
  title     = {An empiricist's view of the ontology of lexical-semantic relations},
  series = {Lexical-Semantic Relations},
  editor    = {Storjohann, Petra},
  publisher = {Benjamins},
  address   = {Amsterdam},
  isbn      = {978 90 272 3138 3},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-48041},
  series    = {Lingvisticae Investigationes Supplementa},
  number    = {28},
  pages     = {115 -- 144},
  year      = {2010},
  abstract  = {Taking a usage-based perspective, lexical-semantic relations and other aspects of lexical meaning are characterised as emerging from language use. At the same time, they shape language use and therefore become manifest in corpus data. This paper discusses how this mutual influence can be taken into account in the study of these relations. An empirically driven methodology is proposed that is, as an initial step, based on self-organising clustering of comprehensive collocation profiles. Several examples demonstrate how this methodology may guide linguists in explicating implicit knowledge of complex semantic structures. Although these example analyses are conducted for written German, the overall methodology is language-independent.},
  language  = {en}
}
@incollection{KeibelBelicaKupietzetal.2011,
  author    = {Keibel, Holger and Belica, Cyril and Kupietz, Marc and Perkuhn, Rainer},
  title     = {Approaching grammar: Detecting, conceptualizing and generalizing paradigmatic variation},
  series = {Grammatik und Korpora. Dritte Internationale Konferenz. Mannheim, 22. - 24.9.2009},
  booktitle = {Grammar \& Corpora 2009. Third International Conference. Mannheim, 22. - 24.9.2009},
  editor    = {Konopka, Marek and Kubczak, Jacqueline and Mair, Christian and Šticha, František and Waßner, Ulrich Hermann},
  publisher = {Narr},
  address   = {T{\"u}bingen},
  isbn      = {978-3-8233-6648-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47783},
  series    = {Korpuslinguistik und interdisziplin{\"a}re Perspektiven auf Sprache},
  number    = {1},
  pages     = {329 -- 355},
  year      = {2011},
  abstract  = {This paper presents ongoing research which is embedded in an empirical-linguistic research program, set out to devise viable research strategies for developing an explanatory theory of grammar as a psychological and social phenomenon. As this phenomenon cannot be studied directly, the program attempts to approach it indirectly through its correlates in language corpora, which is justified by referring to the core tenets of Emergent Grammar. The guiding principle for identifying such corpus correlates of grammatical regularities is to imitate the psychological processes underlying the emergent nature of these regularities. While previous work in this program focused on syntagmatic structures, the current paper goes one step further by investigating schematic structures that involve paradigmatic variation. It introduces and explores a general strategy by which corpus correlates of such structures may be uncovered, and it further outlines how these correlates may be used to study the nature of the psychologically real schematic structures.},
  language  = {en}
}
@incollection{LuengenKeibel2013,
  author    = {L{\"u}ngen, Harald and Keibel, Holger},
  title     = {Zur Erstellung und Interpretation der Zeitverlaufsgrafiken},
  series = {Neuer Wortschatz. Neologismen im Deutschen 2001-2010. Band 2: kiten - Z},
  editor    = {Steffens, Doris and al-Wadi, Doris},
  edition   = {1. Auflage},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  isbn      = {978-3-937241-43-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47870},
  pages     = {561 -- 567},
  year      = {2013},
  language  = {de}
}
@incollection{LuengenKeibel2014,
  author    = {L{\"u}ngen, Harald and Keibel, Holger},
  title     = {Zur Erstellung und Interpretation der Zeitverlaufsgrafiken},
  series = {Neuer Wortschatz. Neologismen im Deutschen 2001-2010. Band 2: kiten - Z},
  editor    = {Steffens, Doris and al-Wadi, Doris},
  edition   = {2., durchgesehene Auflage},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  isbn      = {978-3-937241-43-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47888},
  pages     = {561 -- 567},
  year      = {2014},
  language  = {de}
}
@incollection{LuengenKeibel2015,
  author    = {L{\"u}ngen, Harald and Keibel, Holger},
  title     = {Zur Erstellung und Interpretation der Zeitverlaufsgrafiken},
  series = {Neuer Wortschatz. Neologismen im Deutschen 2001-2010. Band 2: kiten - Z},
  editor    = {Steffens, Doris and al-Wadi, Doris},
  edition   = {3., durchgesehene Auflage},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  isbn      = {978-3-937241-43-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47893},
  pages     = {561 -- 567},
  year      = {2015},
  language  = {de}
}
@misc{PerkuhnBelicaKupietzetal.2009,
  author    = {Perkuhn, Rainer and Belica, Cyril and Kupietz, Marc and Keibel, Holger and Hennig, Sophie},
  title     = {DeReWo: Korpusbasierte Wortformenliste. Technical Report IDS-KL-2009-02},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-50313},
  year      = {2009},
  language  = {de}
}
@techreport{PerkuhnKeibel2009,
  type      = {Working Paper},
  author    = {Perkuhn, Rainer and Keibel, Holger},
  title     = {A brief tutorial on using collocations for uncovering and contrasting meaning potentials of lexical items},
  series = {Working Papers in Corpus-based Linguistics and Language Education No. 3},
  editor    = {Minegishi, Makoto and Kawaguchi, Yuji},
  publisher = {Tokyo University of Foreign Studies},
  address   = {Tokyo},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-47141},
  pages     = {77 -- 91},
  year      = {2009},
  abstract  = {This introductory tutorial describes a strictly corpus-driven approach for uncovering indications for aspects of use of lexical items. These aspects include '(lexical) meaning' in a very broad sense and involve different dimensions, they are established in and emerge from respective discourses. Using data-driven mathematical-statistical methods with minimal (linguistic) premises, a word's usage spectrum is summarized as a collocation profile. Self-organizing methods are applied to visualize the complex similarity structure spanned by these profiles. These visualizations point to the typical aspects of a word's use, and to the common and distinctive aspects of any two words.},
  language  = {en}
}
@inproceedings{KupietzBelicaKeibeletal.2010,
  author    = {Kupietz, Marc and Belica, Cyril and Keibel, Holger and Witt, Andreas},
  title     = {The german reference corpus DeReKo : a primordial sample for linguistic research},
  series = {Proceedings of the 7th International Conference on Language Resources and Evaluation : Workshops \& Tutorials May 17-18, May 22-23, Main Conference May 19-21, Valletta},
  publisher = {ELRA},
  address   = {Paris},
  isbn      = {2-9517408-6-7},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-28379},
  pages     = {1848 -- 1854},
  year      = {2010},
  abstract  = {^This paper describes DeReKo (Deutsches Referenzkorpus), the Archive of General Reference Corpora of Contemporary Written German at the Institut f{\"u}r Deutsche Sprache (IDS) in Mannheim, and the rationale behind its development. We discuss its design, its legal background, how to access it, available metadata, linguistic annotation layers, underlying standards, ongoing developments, and aspects of using the archive for empirical linguistic research. The focus of the paper is on the advantages of DEREKO's design as a primordial sample from which virtual corpora can be drawn for the specific purposes of individual studies. Both concepts, primordial sample and virtual corpus are explained and illustrated in detail. Furthermore, we describe in more detail how DEREKO deals with the fact that all its texts are subject to third parties' intellectual property rights, and how it deals with the issue of replicability, which is particularly challenging given DEREKO's dynamic growth and the possibility to construct from it an open number of virtual corpora.},
  language  = {en}
}
@incollection{PerkuhnBelicaKeibeletal.2015,
  author    = {Perkuhn, Rainer and Belica, Cyril and Keibel, Holger and Kupietz, Marc and L{\"u}ngen, Harald},
  title     = {Valenz und Kookkurrenz},
  series = {Valenz im Fokus. Grammatische und lexikografische Studien; Festschrift f{\"u}r Jacqueline Kubczak},
  editor    = {Dominguez V{\´a}zquez, Maria Jos{\´e} and Eichinger, Ludwig M.},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  isbn      = {978-3-937241-49-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-35442},
  pages     = {175 -- 196},
  year      = {2015},
  language  = {de}
}
@incollection{KupietzKeibel2009,
  author    = {Kupietz, Marc and Keibel, Holger},
  title     = {Gebrauchsbasierte Grammatik: Statistische Regelhaftigkeit},
  series = {Deutsche Grammatik - Regeln, Normen, Sprachgebrauch},
  publisher = {de Gruyter},
  address   = {Berlin [u.a.]},
  doi       = {10.1515/9783110217360.1.33},
  series    = {Jahrbuch / Institut f{\"u}r Deutsche Sprache},
  number    = {" 2008},
  pages     = {33 -- 50},
  year      = {2009},
  abstract  = {Das Ph{\"a}nomen Sprache ist in Form des beobachtbaren Sprachgebrauchs fast allgegenw{\"a}rtig, gleichzeitig bleibt das offenkundig Regel- und Systemhafte dieses Ph{\"a}nomens {\"u}berraschend ungreifbar. Wegen der {\"u}berw{\"a}ltigenden Komplexit{\"a}t nat{\"u}rlicher Sprachen entsteht bei jedem Versuch, dieses Systemhafte in einer Theorie mit explanatorischem Anspruch zu fassen, eine breite Kluft zwischen der angestrebten theoretischen Beschreibungsebene einerseits und der ph{\"a}nomenologisch zug{\"a}nglichen Ebene des Sprachgebrauchs andererseits. Ausgehend von allgemeinen wissenschaftstheoretischen {\"U}berlegungen, wie man angesichts dieser Kluft {\"u}berhaupt zu hinreichend abgesicherten Erkenntnissen f{\"u}r eine explanatorische Theoriebildung kommen kann, betonen die Autoren die Notwendigkeit, sich dem Untersuchungsgegenstand Sprache mit m{\"o}glichst wenigen Vorannahmen {\"u}ber diesen Gegenstand selbst zu n{\"a}hern und sich dabei konsequent von der Empirie leiten zu lassen. Sie werben nachdr{\"u}cklich f{\"u}r eine emergentistische Perspektive auf Sprache, der zufolge alles Regelhafte und Konventionelle in der Sprache ein Epiph{\"a}nomen des Sprachgebrauchs ist und von den Sprachteilnehmern fortlaufend ausgehandelt wird. Eine treibende Kraft hierbei ist, so wird argumentiert, der Begriff der {\"A}hnlichkeit. Auf dieser Grundlage wird schließlich ein Forschungsprogramm entworfen, das die Wirkung des Faktors {\"A}hnlichkeit auf die Sprache nachzuzeichnen und dadurch schrittweise zu {\"a}hnlichen Generalisierungen zu gelangen versucht wie die Sprachgemeinschaft.},
  language  = {de}
}
@book{PerkuhnKeibelKupietz2012,
  author    = {Perkuhn, Rainer and Keibel, Holger and Kupietz, Marc},
  title     = {Korpuslinguistik},
  editor    = {Perkuhn, Rainer and Keibel, Holger and Kupietz, Marc},
  publisher = {Fink},
  address   = {Paderborn},
  isbn      = {978-3-8252-3433-1},
  series    = {UTB : Sprachwissenschaft},
  number    = {3433},
  pages     = {144},
  year      = {2012},
  abstract  = {Das Buch vermittelt Grundlagen und M{\"o}glichkeiten der Korpuslinguistik als sprachwissenschaftliche Methode. Dabei werden alle relevanten Aspekte von der Korpusaufbereitung {\"u}ber verschiedene Formen der Recherche bis hin zu innovativen strukturentdeckenden Ans{\"a}tzen der Analyse abgedeckt.},
  language  = {de}
}
@article{BelicaKeibelKupietzetal.2007,
  author    = {Belica, Cyril and Keibel, Holger and Kupietz, Marc and Perkuhn, Rainer},
  title     = {Web as corpus: Kooperation mit der Universit{\"a}t Bologna},
  series = {Sprachreport / Extra : Informationen und Meinungen zur deutschen Sprache},
  volume    = {23},
  number    = {Extra},
  issn      = {0178-644X},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-28598},
  pages     = {21 -- 25},
  year      = {2007},
  language  = {de}
}
@article{KeibelPerkuhn2006,
  author    = {Keibel, Holger and Perkuhn, Rainer},
  title     = {"W{\"o}rter sind die Schuhe der Gedanken, damit kommt man {\"u}berall hin" : Wissenschaft im Dialog: Das IDS beim Wissenschaftssommer 2006 M{\"u}nchen, 15. - 21. Juli 2006},
  series = {Sprachreport : Informationen und Meinungen zur deutschen Sprache},
  volume    = {22},
  number    = {4},
  issn      = {0178-644X},
  url       = {http://nbn-resolving.de/urn:nbn:de:bsz:mh39-24901},
  pages     = {16 -- 18},
  year      = {2006},
  language  = {de}
}