Direkt zur Hauptnavigation springen Direkt zum Inhalt springen
Letzte Suchanfragen

Ergebnisse für *

Es wurden 9 Ergebnisse gefunden.

Zeige Ergebnisse 1 bis 9 von 9.

Sortieren

  1. Data point selection for genre-aware parsing
    Autor*in: Rehbein, Ines ; Bildhauer, Felix
    Erschienen: 2018
    Verlag:  Prague : Charles University

    In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of... mehr

     

    In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of domain and genre properties, and it is by no means clear what impact each of those has on statistical parsing. In this paper, we investigate how differences between articles in a newspaper corpus relate to the concepts of genre and domain and how they influence parsing performance of a transition-based dependency parser. We do this by applying various similarity measures for data point selection and testing their adequacy for creating genre-aware parsing models.

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Syntaktische Analyse; Automatische Sprachanalyse; Textsorte; Korpus; Sprachstatistik
    Lizenz:

    creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/openAccess
  2. A harmonised testsuite for POS tagging of German social media data
    Autor*in: Rehbein, Ines ; Ruppenhofer, Josef ; Zimmermann, Victor
    Erschienen: 2018
    Verlag:  Vienna, Austria : Austrian academy of sciences

    We present a testsuite for POS tagging German web data. Our testsuite provides the original raw text as well as the gold tokenisations and is annotated for parts-of-speech. The testsuite includes a new dataset for German tweets, with a current size... mehr

     

    We present a testsuite for POS tagging German web data. Our testsuite provides the original raw text as well as the gold tokenisations and is annotated for parts-of-speech. The testsuite includes a new dataset for German tweets, with a current size of 3,940 tokens. To increase the size of the data, we harmonised the annotations in already existing web corpora, based on the Stuttgart-Tübingen Tag Set. The current version of the corpus has an overall size of 48,344 tokens of web data, around half of it from Twitter. We also present experiments, showing how different experimental setups (training set size, additional out-of-domain training data, self-training) influence the accuracy of the taggers. All resources and models will be made publicly available to the research community.

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Korpus; Deutsch; Soziale Software
    Lizenz:

    rightsstatements.org/page/InC/1.0/ ; info:eu-repo/semantics/openAccess
  3. Sprucing up the trees – error detection in treebanks
    Autor*in: Rehbein, Ines ; Ruppenhofer, Josef
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    We present a method for detecting annotation errors in manually and automatically annotated dependency parse trees, based on ensemble parsing in combination with Bayesian inference, guided by active learning. We evaluate our method in different... mehr

     

    We present a method for detecting annotation errors in manually and automatically annotated dependency parse trees, based on ensemble parsing in combination with Bayesian inference, guided by active learning. We evaluate our method in different scenarios: (i) for error detection in dependency treebanks and (ii) for improving parsing accuracy on in- and out-of-domain data.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Aufsatz aus einem Sammelband
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Automatische Spracherkennung; Annotation; Parser
    Lizenz:

    creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/openAccess
  4. Data point selection for genre-aware parsing
    Autor*in: Rehbein, Ines ; Bildhauer, Felix
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of... mehr

     

    In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of domain and genre properties, and it is by no means clear what impact each of those has on statistical parsing. In this paper, we investigate how differences between articles in a newspaper corpus relate to the concepts of genre and domain and how they influence parsing performance of a transition-based dependency parser. We do this by applying various similarity measures for data point selection and testing their adequacy for creating genre-aware parsing models.

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Parsing; Korpus; Textsorte
    Lizenz:

    creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/openAccess
  5. Evaluating LSTM models for grammatical function labelling
    Autor*in: Do, Bich-Ngoc ; Rehbein, Ines
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our... mehr

     

    To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker).

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Automatische Sprachverarbeitung; Syntaktische Analyse; Parser; Deutsch
    Lizenz:

    creativecommons.org/licenses/by/4.0/deed.de ; info:eu-repo/semantics/openAccess
  6. Universal Dependencies are hard to parse – or are they?
    Autor*in: Rehbein, Ines ; Steen, Julius ; Do, Bich-Ngoc ; Frank, Anette
    Erschienen: 2018
    Verlag:  Linköping, Schweden : Linköping University Electronic Press

    Universal Dependency (UD) annotations, despite their usefulness for cross-lingual tasks and semantic applications, are not optimised for statistical parsing. In the paper, we ask what exactly causes the decrease in parsing accuracy when training a... mehr

     

    Universal Dependency (UD) annotations, despite their usefulness for cross-lingual tasks and semantic applications, are not optimised for statistical parsing. In the paper, we ask what exactly causes the decrease in parsing accuracy when training a parser on UD-style annotations and whether the effect is similarly strong for all languages. We conduct a series of experiments where we systematically modify individual annotation decisions taken in the UD scheme and show that this results in an increased accuracy for most, but not for all languages. We show that the encoding in the UD scheme, in particular the decision to encode content words as heads, causes an increase in dependency length for nearly all treebanks and an increase in arc direction entropy for many languages, and evaluate the effect this has on parsing accuracy.

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Syntax; Annotation; Parser; Universalgrammatik
    Lizenz:

    creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/openAccess
  7. What do we need to know about an unknown word when parsing German
    Autor*in: Do, Bich-Ngoc ; Rehbein, Ines ; Frank, Anette
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German. We present an extrinsic evaluation where we use the compound embeddings as input to a neural dependency... mehr

     

    We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German. We present an extrinsic evaluation where we use the compound embeddings as input to a neural dependency parser and compare the results to the ones obtained with other types of embeddings. Our evaluation shows that adding compound embeddings yields a significant improvement of 2% LAS over using word embeddings when no POS information is available. When adding POS embeddings to the input, however, the effect levels out. This suggests that it is not the missing information about the semantics of the unknown words that causes problems for parsing German, but the lack of morphological information for unknown words. To augment our evaluation, we also test the new embeddings in a language modelling task that requires both syntactic and semantic information.

     
    Export in Literaturverwaltung
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Konferenzveröffentlichung
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Deutsch; Kompositum; Automatische Spracherkennung
    Lizenz:

    creativecommons.org/licenses/by/4.0/deed.de ; info:eu-repo/semantics/openAccess
  8. Authorship attribution with convolutional neural networks and POS-eliding
    Autor*in: Hitschler, Julian ; van den Berg, Esther ; Rehbein, Ines
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications. In order to investigate the effect of domain biases, we obscure words below a certain frequency threshold, retaining... mehr

     

    We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications. In order to investigate the effect of domain biases, we obscure words below a certain frequency threshold, retaining only their POS-tags. This procedure improves test performance due to better generalization on unseen data. Using our method, we are able to predict the authors of scientific publications in the same discipline at levels well above chance.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Aufsatz aus einem Sammelband
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Autorschaft; Computerlinguistik
    Lizenz:

    creativecommons.org/licenses/by/4.0/ ; info:eu-repo/semantics/openAccess
  9. Detecting annotation noise in automatically labelled data
    Autor*in: Rehbein, Ines ; Ruppenhofer, Josef
    Erschienen: 2018
    Verlag:  Stroudsburg PA, USA : The Association for Computational Linguistics

    We introduce a method for error detection in automatically annotated text, aimed at supporting the creation of high-quality language resources at affordable cost. Our method combines an unsupervised generative model with human supervision from active... mehr

     

    We introduce a method for error detection in automatically annotated text, aimed at supporting the creation of high-quality language resources at affordable cost. Our method combines an unsupervised generative model with human supervision from active learning. We test our approach on in-domain and out-of-domain data in two languages, in AL simulations and in a real world setting. For all settings, the results show that our method is able to detect annotation errors with high precision and high recall.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: BASE Fachausschnitt Germanistik
    Sprache: Englisch
    Medientyp: Aufsatz aus einem Sammelband
    Format: Online
    DDC Klassifikation: Sprache (400)
    Schlagworte: Computerlinguistik; Automatische Sprachverarbeitung; Annotation; Fehleranalyse
    Lizenz:

    rightsstatements.org/page/InC/1.0/ ; info:eu-repo/semantics/openAccess