@article{StedePeldszus2012,
  author    = {Stede, Manfred and Peldszus, Andreas},
  title     = {The role of illocutionary status in the usage conditions of causal connectives and in coherence relations},
  series = {Journal of pragmatics : an interdisciplinary journal of language studies},
  volume    = {44},
  journal   = {Journal of pragmatics : an interdisciplinary journal of language studies},
  number    = {2},
  publisher = {Elsevier},
  address   = {Amsterdam},
  issn      = {0378-2166},
  doi       = {10.1016/j.pragma.2012.01.004},
  pages     = {214 -- 229},
  year      = {2012},
  abstract  = {The meaning of linguistic connectives has often been characterized in terms of their position in a bipartite (semantic, pragmatic) or a tripartite (content, epistemic, speech act) structure of domains, depending on what kinds of entities are being connected (largely: propositions or speech acts). This paper argues that a more fine-grained analysis can be achieved by directing some more attention to the characterization of the entities being related. We propose an inventory of categories of illocutionary status for labelling the spans that are being connected. On this basis, the distinction between the content and the epistemic domain, in particular, can be made more explicit. Focusing on the group of causal connectives in German, we conducted a corpus annotation study from which we derived distinct pragmatic 'usage profiles' of the most frequent causal connectives. Finally, we offer some suggestions on the role of illocutions in relation-based accounts of discourse structure.},
  language  = {en}
}
@book{StedeChiarcosGrabskietal.2005,
  author    = {Stede, Manfred and Chiarcos, Christian and Grabski, Michael and Lagerwerf, Luuk},
  title     = {Salience in discurse : multidisciplinary approaches to discourse 2005},
  series = {Uitgaven Stichting Neerlandistiek VU},
  volume    = {49},
  journal   = {Uitgaven Stichting Neerlandistiek VU},
  publisher = {Nodus-Publ; Stichting Neerlandistiek VU},
  address   = {M{\"u}nster; Amsterdam},
  isbn      = {3-89323-749-6},
  pages     = {153 S.},
  year      = {2005},
  language  = {en}
}
@article{Stede2008,
  author    = {Stede, Manfred},
  title     = {RST revisited : disentangling nuclearity},
  isbn      = {978-90-272-3109-3},
  year      = {2008},
  language  = {en}
}
@article{Stede2002,
  author    = {Stede, Manfred},
  title     = {Polibox: Generating desciptions, comparisons, and recommendations from a database},
  isbn      = {1-55860- 899-0},
  year      = {2002},
  language  = {en}
}
@book{OlsenStiebelsBierwischetal.2019,
  author    = {Olsen, Susan and Stiebels, Barbara and Bierwisch, Manfred and Zimmermann, Ilse and Cavar, Damir and Georgi, Doreen and Bacskai-Atkari, Julia and Alexiadou, Artemis and Błaszczak, Joanna and M{\"u}ller, Gereon and Šim{\´i}k, Radek and Meinunger, Andr{\´e} and Thiersch, Craig and Arnhold, Anja and F{\´e}ry, Caroline and Bayer, Josef and Titov, Elena and Fominyam, Henry and Tran, Thuan and Bornkessel-Schlesewsky, Ina D. and Schlesewsky, Matthias and Zimmermann, Malte and H{\"a}ussler, Jana and Mucha, Anne and Schmidt, Andreas and Weskott, Thomas and Wierzba, Marta and Stede, Manfred and Skopeteas, Stavros and Gafos, Adamantios I. and Haider, Hubert and Wunderlich, Dieter and Staudacher, Peter and Rauh, Gisa},
  title     = {Of Trees and Birds},
  editor    = {Brown, Jessica M. M. and Schmidt, Andreas and Wierzba, Marta},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-457-9},
  doi       = {10.25932/publishup-42654},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-426542},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {xvi, 435},
  year      = {2019},
  abstract  = {Gisbert Fanselow's work has been invaluable and inspiring to many ­researchers working on syntax, morphology, and information ­structure, both from a ­theoretical and from an experimental perspective. This ­volume comprises a collection of articles dedicated to Gisbert on the occasion of his 60th birthday, covering a range of topics from these areas and beyond. The contributions have in ­common that in a broad sense they have to do with language structures (and thus trees), and that in a more specific sense they have to do with birds. They thus cover two of Gisbert's major interests in- and outside of the linguistic world (and ­perhaps even at the interface).},
  language  = {en}
}
@article{Stede2019,
  author    = {Stede, Manfred},
  title     = {Noch kindlich oder schon jugendlich? Oder gar erwachsen?},
  series = {Of trees and birds. A Festschrift for Gisbert Fanselow},
  journal   = {Of trees and birds. A Festschrift for Gisbert Fanselow},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-457-9},
  doi       = {10.25932/publishup-43256},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-432569},
  pages     = {323 -- 334},
  year      = {2019},
  language  = {de}
}
@article{TaboadaBrookeTofiloskietal.2011,
  author    = {Taboada, Maite and Brooke, Julian and Tofiloski, Milan and Voll, Kimberly and Stede, Manfred},
  title     = {Lexicon-Based methods for sentiment analysis},
  series = {Computational linguistics},
  volume    = {37},
  journal   = {Computational linguistics},
  number    = {2},
  publisher = {MIT Press},
  address   = {Cambridge},
  issn      = {0891-2017},
  pages     = {267 -- 307},
  year      = {2011},
  abstract  = {We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and on completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.},
  language  = {en}
}
@book{Stede2007,
  author    = {Stede, Manfred},
  title     = {Korpusgest{\"u}tzte Textanalyse : Grundz{\"u}ge der Ebenen-orientierten Textlinguistik},
  publisher = {Narr},
  address   = {T{\"u}bingen},
  isbn      = {978-3-8233-6301-9},
  issn      = {0941-8105},
  pages     = {207 S.},
  year      = {2007},
  language  = {de}
}
@article{StedeHuang2012,
  author    = {Stede, Manfred and Huang, Chu-Ren},
  title     = {Inter-operability and reusability the science of annotation},
  series = {Language resources and evaluation},
  volume    = {46},
  journal   = {Language resources and evaluation},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1574-020X},
  doi       = {10.1007/s10579-011-9164-x},
  pages     = {91 -- 94},
  year      = {2012},
  abstract  = {Annotating linguistic data has become a major field of interest, both for supplying the necessary data for machine learning approaches to NLP applications, and as a research issue in its own right. This comprises issues of technical formats, tools, and methodologies of annotation. We provide a brief overview of these notions and then introduce the papers assembled in this special issue.},
  language  = {en}
}
@article{StedeKuhn2009,
  author    = {Stede, Manfred and Kuhn, Florian},
  title     = {Identifying the content zones of German court decisions},
  isbn      = {978-3-642- 03423-7},
  year      = {2009},
  language  = {en}
}
@book{StedeMamprinPeldszusetal.2015,
  author    = {Stede, Manfred and Mamprin, Sara and Peldszus, Andreas and Herzog, Andr{\´e} and Kaupat, David and Chiarcos, Christian and Warzecha, Saskia},
  title     = {Handbuch Textannotation},
  editor    = {Stede, Manfred},
  isbn      = {978-3-86956-343-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-82761},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {xvii, 209},
  year      = {2015},
  abstract  = {Das Potsdamer Kommentarkorpus ist eine Sammlung von Zeitungstexten, die dem Genre 'Kommentar' zuzuordnen sind. Der {\"o}ffentlich verf{\"u}gbare Teil besteht aus 175 Texten aus der M{\"a}rkischen Allgemeinen Zeitung, die hinsichtlich Syntax, Koreferenz, Konnektoren und Rhetorische Struktur manuell annotiert wurden. Weitere Ebenen werden bei zuk{\"u}nftigen Korpusversionen hinzukommen. Dieses Buch enth{\"a}lt die Annotationsrichtlinien, die der Bearbeitung des {\"o}ffentlichen Teils des Korpus zugrunde lagen, sowie auch anderer Teile, bei denen mit weiteren Annotationsebenen experimentiert wurde. Die meisten der Richtlinien werden auch f{\"u}r {\"a}hnliche Text-Genres und f{\"u}r andere Sprachen verwendbar sein.},
  language  = {de}
}
@article{Stede2020,
  author    = {Stede, Manfred},
  title     = {From connectives to coherence relations},
  series = {Revue roumaine de linguistique : RRL = Romanian review of linguistics},
  volume    = {65},
  journal   = {Revue roumaine de linguistique : RRL = Romanian review of linguistics},
  number    = {3},
  publisher = {Ed. Academiei Rom{\^a}ne},
  address   = {Bucure{\c{s}}ti},
  issn      = {0035-3957},
  pages     = {213 -- 233},
  year      = {2020},
  abstract  = {The notion of coherence relations is quite widely accepted in general, but concrete proposals differ considerably on the questions of how they should be motivated, which relations are to be assumed, and how they should be defined. This paper takes a "bottom-up" perspective by assessing the contribution made by linguistic signals (connectives), using insights from the relevant literature as well as verification by practical text annotation. We work primarily with the German language here and focus on the realm of contrast. Thus, we suggest a new inventory of contrastive connective functions and discuss their relationship to contrastive coherence relations that have been proposed in earlier work.},
  language  = {en}
}
@misc{SaintDizierStede2017,
  author    = {Saint-Dizier, Patrick and Stede, Manfred},
  title     = {Foundations of the language of argumentation},
  series = {Argument \& computation},
  volume    = {8},
  journal   = {Argument \& computation},
  number    = {2 Special issue},
  publisher = {IOS Press},
  address   = {Amsterdam},
  issn      = {1946-2166},
  doi       = {10.3233/AAC-170018},
  pages     = {91 -- 93},
  year      = {2017},
  language  = {en}
}
@article{Stede2004,
  author    = {Stede, Manfred},
  title     = {Does discourse processing need discourse topics?},
  issn      = {0301-4428},
  year      = {2004},
  language  = {en}
}
@article{Stede2008,
  author    = {Stede, Manfred},
  title     = {Disambiguating rhetorical structure},
  issn      = {1570-7075},
  doi       = {10.1007/s11168-008-9053-7},
  year      = {2008},
  abstract  = {Empirical studies of text coherence often use tree-like structures in the spirit of Rhetorical Structure Theory (RST) as representational device. This paper identifies several sources of ambiguity in RST-inspired trees and argues that such structures are therefore not as explanatory as a text representation should be. As an alternative, an approach toward multi-level annotation (MLA) of texts is proposed, which separates the information into distinct levels of representation, in particular: referential structure, thematic structure, conjunctive relations, and intentional structure. Levels are conceptually built upon each other, and human annotators can produce them using a dedicated software environment. We argue that the resulting multi-level corpora are descriptively more adequate, and as a resource are more useful than RST-style treebanks.},
  language  = {en}
}
@article{Stede2002,
  author    = {Stede, Manfred},
  title     = {DiMLex: a lexical approach to discourse markers},
  year      = {2002},
  language  = {en}
}
@article{LuedelingRitzStedeetal.2016,
  author    = {L{\"u}deling, Anke and Ritz, Julia and Stede, Manfred and Zeldes, Amir},
  title     = {Corpus Linguistics and Information Structure Research},
  series = {The Oxford handbook of information structure},
  journal   = {The Oxford handbook of information structure},
  publisher = {Oxford University Press},
  address   = {Oxford},
  isbn      = {978-0-19-964267-0},
  pages     = {599 -- 617},
  year      = {2016},
  language  = {en}
}
@article{StedeSchefflerMendes2019,
  author    = {Stede, Manfred and Scheffler, Tatjana and Mendes, Amalia},
  title     = {Connective-Lex},
  series = {Discours : revue de linguistique, psycholinguistique et informatique},
  journal   = {Discours : revue de linguistique, psycholinguistique et informatique},
  number    = {24},
  publisher = {Universit{\´e} de Paris-Sorbonne},
  address   = {Paris},
  issn      = {1963-1723},
  doi       = {10.4000/discours.10098},
  pages     = {36},
  year      = {2019},
  abstract  = {In this paper, we present a tangible outcome of the TextLink network: a joint online database project displaying and linking existing and newly-created lexicons of discourse connectives in multiple languages. We discuss the definition and demarcation of the class of connectives that should be included in such a resource, and present the syntactic, semantic/pragmatic, and lexicographic information we collected. Further, the technical implementation of the database and the search functionality are presented. We discuss how the multilingual integration of several connective lexicons provides added value for linguistic researchers and other users interested in connectives, by allowing crosslinguistic comparison and a direct linking between discourse relational devices in different languages. Finally, we provide pointers for possible future extensions both in breadth (i.e., by adding lexicons for additional languages) and depth (by extending the information provided for each connective item and by strengthening the crosslinguistic links).},
  language  = {en}
}
@article{Stede2008,
  author    = {Stede, Manfred},
  title     = {Connective-based local coherence analysis : a lexicon for recognizing causal relationships},
  isbn      = {978-1-904-98793-2},
  year      = {2008},
  language  = {en}
}
@article{Stede2008,
  author    = {Stede, Manfred},
  title     = {Computerlinguistik und Textanalyse},
  isbn      = {978-3-8233- 6432-0},
  year      = {2008},
  language  = {de}
}
@article{WulffBuschhueterWestphaletal.2020,
  author    = {Wulff, Peter and Buschh{\"u}ter, David and Westphal, Andrea and Nowak, Anna and Becker, Lisa and Robalino, Hugo and Stede, Manfred and Borowski, Andreas},
  title     = {Computer-based classification of preservice physics teachers' written reflections},
  series = {Journal of science education and technology},
  volume    = {30},
  journal   = {Journal of science education and technology},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1059-0145},
  doi       = {10.1007/s10956-020-09865-1},
  pages     = {1 -- 15},
  year      = {2020},
  abstract  = {Reflecting in written form on one's teaching enactments has been considered a facilitator for teachers' professional growth in university-based preservice teacher education. Writing a structured reflection can be facilitated through external feedback. However, researchers noted that feedback in preservice teacher education often relies on holistic, rather than more content-based, analytic feedback because educators oftentimes lack resources (e.g., time) to provide more analytic feedback. To overcome this impediment to feedback for written reflection, advances in computer technology can be of use. Hence, this study sought to utilize techniques of natural language processing and machine learning to train a computer-based classifier that classifies preservice physics teachers' written reflections on their teaching enactments in a German university teacher education program. To do so, a reflection model was adapted to physics education. It was then tested to what extent the computer-based classifier could accurately classify the elements of the reflection model in segments of preservice physics teachers' written reflections. Multinomial logistic regression using word count as a predictor was found to yield acceptable average human-computer agreement (F1-score on held-out test dataset of 0.56) so that it might fuel further development towards an automated feedback tool that supplements existing holistic feedback for written reflections with data-based, analytic feedback.},
  language  = {en}
}
@misc{AfantenosPeldszusStede2018,
  author    = {Afantenos, Stergos and Peldszus, Andreas and Stede, Manfred},
  title     = {Comparing decoding mechanisms for parsing argumentative structures},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1062},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47052},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-470527},
  pages     = {18},
  year      = {2018},
  abstract  = {Parsing of argumentative structures has become a very active line of research in recent years. Like discourse parsing or any other natural language task that requires prediction of linguistic structures, most approaches choose to learn a local model and then perform global decoding over the local probability distributions, often imposing constraints that are specific to the task at hand. Specifically for argumentation parsing, two decoding approaches have been recently proposed: Minimum Spanning Trees (MST) and Integer Linear Programming (ILP), following similar trends in discourse parsing. In contrast to discourse parsing though, where trees are not always used as underlying annotation schemes, argumentation structures so far have always been represented with trees. Using the 'argumentative microtext corpus' [in: Argumentation and Reasoned Action: Proceedings of the 1st European Conference on Argumentation, Lisbon 2015 / Vol. 2, College Publications, London, 2016, pp. 801-815] as underlying data and replicating three different decoding mechanisms, in this paper we propose a novel ILP decoder and an extension to our earlier MST work, and then thoroughly compare the approaches. The result is that our new decoder outperforms related work in important respects, and that in general, ILP and MST yield very similar performance.},
  language  = {en}
}
@article{AfantenosPeldszusStede2018,
  author    = {Afantenos, Stergos and Peldszus, Andreas and Stede, Manfred},
  title     = {Comparing decoding mechanisms for parsing argumentative structures},
  series = {Argument \& Computation},
  volume    = {9},
  journal   = {Argument \& Computation},
  number    = {3},
  publisher = {IOS Press},
  address   = {Amsterdam},
  issn      = {1946-2166},
  doi       = {10.3233/AAC-180033},
  pages     = {177 -- 192},
  year      = {2018},
  abstract  = {Parsing of argumentative structures has become a very active line of research in recent years. Like discourse parsing or any other natural language task that requires prediction of linguistic structures, most approaches choose to learn a local model and then perform global decoding over the local probability distributions, often imposing constraints that are specific to the task at hand. Specifically for argumentation parsing, two decoding approaches have been recently proposed: Minimum Spanning Trees (MST) and Integer Linear Programming (ILP), following similar trends in discourse parsing. In contrast to discourse parsing though, where trees are not always used as underlying annotation schemes, argumentation structures so far have always been represented with trees. Using the 'argumentative microtext corpus' [in: Argumentation and Reasoned Action: Proceedings of the 1st European Conference on Argumentation, Lisbon 2015 / Vol. 2, College Publications, London, 2016, pp. 801-815] as underlying data and replicating three different decoding mechanisms, in this paper we propose a novel ILP decoder and an extension to our earlier MST work, and then thoroughly compare the approaches. The result is that our new decoder outperforms related work in important respects, and that in general, ILP and MST yield very similar performance.},
  language  = {en}
}
@article{KruegerLukowiakSonntagetal.2017,
  author    = {Kr{\"u}ger, K. R. and Lukowiak, A. and Sonntag, J. and Warzecha, Saskia and Stede, Manfred},
  title     = {Classifying news versus opinions in newspapers},
  series = {Natural language engineering},
  volume    = {23},
  journal   = {Natural language engineering},
  publisher = {Cambridge Univ. Press},
  address   = {Cambridge},
  issn      = {1351-3249},
  doi       = {10.1017/S1351324917000043},
  pages     = {687 -- 707},
  year      = {2017},
  abstract  = {Newspaper text can be broadly divided in the classes 'opinion' (editorials, commentary, letters to the editor) and 'neutral' (reports). We describe a classification system for performing this separation, which uses a set of linguistically motivated features. Working with various English newspaper corpora, we demonstrate that it significantly outperforms bag-of-lemma and PoS-tag models. We conclude that the linguistic features constitute the best method for achieving robustness against change of newspaper or domain.},
  language  = {en}
}
@article{ChiarcosRitzStede2012,
  author    = {Chiarcos, Christian and Ritz, Julia and Stede, Manfred},
  title     = {By all these lovely tokens... Merging conflicting tokenizations},
  series = {Language resources and evaluation},
  volume    = {46},
  journal   = {Language resources and evaluation},
  number    = {1},
  publisher = {Springer},
  address   = {Dordrecht},
  issn      = {1574-020X},
  doi       = {10.1007/s10579-011-9161-0},
  pages     = {53 -- 74},
  year      = {2012},
  abstract  = {Given the contemporary trend to modular NLP architectures and multiple annotation frameworks, the existence of concurrent tokenizations of the same text represents a pervasive problem in everyday's NLP practice and poses a non-trivial theoretical problem to the integration of linguistic annotations and their interpretability in general. This paper describes a solution for integrating different tokenizations using a standoff XML format, and discusses the consequences from a corpus-linguistic perspective.},
  language  = {en}
}
@article{GrabskiStede2006,
  author    = {Grabski, Michael and Stede, Manfred},
  title     = {Bei : intraclausal coherence relations illustrated with a German preposition},
  issn      = {0163-853X},
  doi       = {10.1207/s15326950dp4102_5},
  year      = {2006},
  abstract  = {Coherence relations are typically taken to link two clauses or larger units and to be signaled at the text surface by conjunctions and certain adverbials. Relations, however, also can hold within clauses, indicated by prepositions like despite, due to, or in case of, when these have an internal argument denoting an eventuality. Although these prepositions act as reliable cues to indicate a specific relation, others are lexically more neutral. We investigated this situation for the German preposition bei, which turns out to be highly ambiguous. We demonstrate the range of readings in a corpus study, proposing 6 more specific prepositions as a comprehensive substitution set. All these uses of bei share a common kernel meaning, which is missed by the standard accounts that assume lexical polysemy. We examine the range of coherence relations that can be signaled by bei and provide some factors here supporting the disambiguation task in a framework of discourse interpretation},
  language  = {en}
}
@article{Stede2020,
  author    = {Stede, Manfred},
  title     = {Automatic argumentation mining and the role of stance and sentiment},
  series = {Journal of argumentation in context},
  volume    = {9},
  journal   = {Journal of argumentation in context},
  number    = {1},
  publisher = {John Benjamins Publishing Co.},
  address   = {Amsterdam},
  issn      = {2211-4742},
  doi       = {10.1075/jaic.00006.ste},
  pages     = {19 -- 41},
  year      = {2020},
  abstract  = {Argumentation mining is a subfield of Computational Linguistics that aims (primarily) at automatically finding arguments and their structural components in natural language text. We provide a short introduction to this field, intended for an audience with a limited computational background. After explaining the subtasks involved in this problem of deriving the structure of arguments, we describe two other applications that are popular in computational linguistics: sentiment analysis and stance detection. From the linguistic viewpoint, they concern the semantics of evaluation in language. In the final part of the paper, we briefly examine the roles that these two tasks play in argumentation mining, both in current practice, and in possible future systems.},
  language  = {en}
}
@article{SchaeferStede2021,
  author    = {Sch{\"a}fer, Robin and Stede, Manfred},
  title     = {Argument mining on twitter},
  series = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG},
  volume    = {63},
  journal   = {Information technology : it ; Methoden und innovative Anwendungen der Informatik und Informationstechnik ; Organ der Fachbereiche 3 und 4 der GI e.V. und des Fachbereichs 6 der ITG},
  number    = {1},
  publisher = {De Gruyter},
  address   = {Berlin},
  issn      = {1611-2776},
  doi       = {10.1515/itit-2020-0053},
  pages     = {45 -- 58},
  year      = {2021},
  abstract  = {In the last decade, the field of argument mining has grown notably. However, only relatively few studies have investigated argumentation in social media and specifically on Twitter. Here, we provide the, to our knowledge, first critical in-depth survey of the state of the art in tweet-based argument mining. We discuss approaches to modelling the structure of arguments in the context of tweet corpus annotation, and we review current progress in the task of detecting argument components and their relations in tweets. We also survey the intersection of argument mining and stance detection, before we conclude with an outlook.},
  language  = {en}
}
@article{DipperGoetzeStedeetal.2004,
  author    = {Dipper, Stefanie and G{\"o}tze, Michael and Stede, Manfred and Wegst, Tillmann},
  title     = {ANNIS},
  series = {Interdisciplinary studies on information structure : ISIS ; working papers of the SFB 632},
  journal   = {Interdisciplinary studies on information structure : ISIS ; working papers of the SFB 632},
  number    = {1},
  issn      = {1866-4725},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-8432},
  pages     = {245 -- 279},
  year      = {2004},
  abstract  = {In this paper, we discuss the design and implementation of our first version of the database "ANNIS" ("ANNotation of Information Structure"). For research based on empirical data, ANNIS provides a uniform environment for storing this data together with its linguistic annotations. A central database promotes standardized annotation, which facilitates interpretation and comparison of the data. ANNIS is used through a standard web browser and offers tier-based visualization of data and annotations, as well as search facilities that allow for cross-level and cross-sentential queries. The paper motivates the design of the system, characterizes its user interface, and provides an initial technical evaluation of ANNIS with respect to data size and query processing.},
  language  = {en}
}
@article{ChiarcosDipperGoetzeetal.2008,
  author    = {Chiarcos, Christian and Dipper, Stefanie and G{\"o}tze, Michael and Leser, Ulf and L{\"u}deling, Anke and Ritz, Julia and Stede, Manfred},
  title     = {A flexible framework for integrating annotations from different tools and tag sets},
  issn      = {1248-9433},
  year      = {2008},
  abstract  = {We present a general framework for integrating annotations from different tools and tag sets. When annotating corpora at multiple linguistic levels, annotators may use different expert tools for different phenomena or types of annotation. These tools employ different data models and accompanying approaches to visualization, and they produce different output formats. For the purposes of uniformly processing these outputs, we developed a pivot format called PAULA, along with converters to and from tool formats. Different annotations are not only integrated at the level of data format, but are also joined on the level of conceptual representation. For this purpose, we introduce OLiA, an ontology of linguistic annotations that mediates between alternative tag sets that cover the same class of linguistic phenomena. All components are integrated in the linguistic information system ANNIS : Annotation tool output is converted to the pivot format PAULA and read into a database where the data can be visualized, queried, and evaluated across multiple layers. For cross-tag set querying and statistical evaluation, ANNIS uses the ontology of linguistic annotations. Finally, ANNIS is also tied to a machine learning component for semiautomatic annotation.},
  language  = {en}
}