Refine
Document Type
- Part of a Book (9)
- Article (2)
- Conference Proceeding (1)
Has Fulltext
- yes (12) (remove)
Keywords
- Annotation (12) (remove)
Publicationstate
- Postprint (12) (remove)
Reviewstate
- (Verlags)-Lektorat (9)
- Peer-Review (2)
Publisher
Automatic summarization systems usually are trained and evaluated in a particular domain with fixed data sets. When such a system is to be applied to slightly different input, labor- and cost-intensive annotations have to be created to retrain the system. We deal with this problem by providing users with a GUI which allows them to correct automatically produced imperfect summaries. The corrected summary in turn is added to the pool of training data. The performance of the system is expected to improve as it adapts to the new domain.
In this contribution we present some work of the R&D European project “LIRICS” and of the ISO/TC 37/SC 4 committee related to the topic of interoperability and re-use of language resources. We introduce some basic mechanisms of the standardization work in ISO and describe in more details the general approach on how to cope with the annotation of language data within ISO.
Transkriptionswerkzeuge sind spezialisierte Softwaretools für die Transkription und Annotation von Audio- oder Videoaufzeichnungen gesprochener Sprache. Dieses Kapitel erklärt einleitend, worin der zusätzliche Nutzen solcher Werkzeuge gegenüber einfacher Textverarbeitungssoftware liegt, und gibt dann einen Überblick über grundlegende Prinzipien und einige weitverbreitete Tools dieser Art. Am Beispiel der Editoren FOLKER und OrthoNormal wird schließlich der praktische Einsatz zweier Werkzeuge in den Arbeitsabläufen eines Korpusprojekts illustriert.
Diese Fallstudie untersucht die quantitative Verteilung von direkten und nicht-direkten Formen von Redewiedergabe im Vergleich zwischen zwei Literaturtypen: Hochliteratur - definiert als Werke, die auf der Auswahlliste von Literaturpreisen standen - und Heftromanen - massenproduzierten Erzählwerken, die zumeist über den Zeitschriftenhandel vertrieben werden. Die Studie geht von manuell annotierten Daten aus und überprüft daran die Verlässlichkeit automatischer Annotationswerkzeuge, die im Anschluss eingesetzt werden, um eine Untersuchung von insgesamt 250 Volltexten durchzuführen. Es kann nachgewiesen werden, dass sich die Literaturtypen sowie auch unterschiedliche Genres von Heftromanen hinsichtlich der verwendeten Wiedergabeformen unterscheiden.
This article discusses questions concerning the creation, annotation and sharing of spoken language corpora. We use the Hamburg Map Task Corpus (HAMATAC), a small corpus in which advanced learners of German were recorded solving a map task, as an example to illustrate our main points. We first give an overview of the corpus creation and annotation process including recording, metadata documentation, transcription and semi-automatic annotation of the data. We then discuss the manual annotation of disfluencies as an example case in which many of the typical and challenging problems for data reuse – in particular the reliability of interpretative annotations – are revealed.
This study examines what kind of cues and constraints for discourse interpretation can be derived from the logical and generic document structure of complex texts by the example of scientific journal articles. We performed statistical analysis on a corpus of scientific articles annotated on different annotations layers within the framework of XML-based multi-layer annotation. We introduce different discourse segment types that constrain the textual domains in which to identify rhetorical relation spans, and we show how a canonical sequence of text type structure categories is derived from the corpus annotations. Finally, we demonstrate how and which text type structure categories assigned to complex discourse segments of the type “block” statistically constrain the occurrence of rhetorical relation types.
The paper presents the results of a joint effort of a group of multimodality researchers and tool developers to improve the interoperability between several tools used for the annotation and analysis of multimodality. Each of the tools has specific strengths so that a variety of different tools, working on the same data, can be desirable for project work. However this usually requires tedious conversion between formats. We propose a common exchange format for multimodal annotation, based on the annotation graph (AG) formalism, which is supported by import and export routines in the respective tools. In the current version of this format the common denominator information can be reliably exchanged between the tools, and additional information can be stored in a standardized way.
Integrated Linguistic Annotation Models and Their Application in the Domain of Antecedent Detection
(2011)
Seamless integration of various, often heterogeneous linguistic resources in terms of their output formats and a combined analysis of the respective annotation layers are crucial tasks for linguistic research. After a decade of concentration on the development of formats to structure single annotations for specific linguistic issues, in the last years a variety of specifications to store multiple annotations over the same primary data has been developed. The paper focuses on the integration of the knowledge resource logical document structure information into a text document to enhance the task of automatic anaphora resolution both for the task of candidate detection and antecedent selection. The paper investigates data structures necessary for knowledge integration and retrieval.
Different Views on Markup
(2010)
In this chapter, two different ways of grouping information represented in document markup are examined: annotation levels, referring to conceptual levels of description, and annotation layers, referring to the technical realisation of markup using e.g. document grammars. In many current XML annotation projects, multiple levels are integrated into one layer, often leading to the problem of having to deal with overlapping hierarchies. As a solution, we propose a framework for XML-based multiple, independent XML annotation layers for one text, based on an abstract representation of XML documents with logical predicates. Two realisations of the abstract representation are presented, a Prolog fact base format together with an application architecture, and a specification for XML native databases. We conclude with a discussion of projects that have currently adopted this framework.
This article shows that the TEI tag set for feature structures can be adopted to represent a heterogeneous set of linguistic corpora. The majority of corpora is annotated using markup languages that are based on the Annotation Graph framework, the upcoming Linguistic Annotation Format ISO standard, or according to tag sets defined by or based upon the TEI guidelines. A unified representation comprises the separation of conceptually different annotation layers contained in the original corpus data (e.g. syntax, phonology, and semantics) into multiple XML files. These annotation layers are linked to each other implicitly by the identical textual content of all files. A suitable data structure for the representation of these annotations is a multi-rooted tree that again can be represented by the TEI and ISO tag set for feature structures. The mapping process and representational issues are discussed as well as the advantages and drawbacks associated with the use of the TEI tag set for feature structures as a storage and exchange format for linguistically annotated data.
Discourse segmentation is the division of a text into minimal discourse segments, which form the leaves in the trees that are used to represent discourse structures. A definition of elementary discourse segments in German is provided by adapting widely used segmentation principles for English minimal units, while considering punctuation, morphology, sytax, and aspects of the logical document structure of a complex text type, namely scientific articles. The algorithm and implementation of a discourse segmenter based on these principles is presented, as well an evaluation of test runs.