@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} } @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{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{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{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{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} } @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{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} } @article{Stede2008, author = {Stede, Manfred}, title = {Computerlinguistik und Textanalyse}, isbn = {978-3-8233- 6432-0}, year = {2008}, language = {de} }