Dieses Lehrbuch bietet eine umfassende Einführung in Grundlagen und das führende deutschsprachige Werk zur Computerlinguistik und Sprachtechnologie Versehen mit digitalem Wasserzeichen, DRM-frei; Erhältliche Formate: PDF. Dieses Lehrbuch bietet eine umfassende Einführung in Grundlagen und Methoden Kai-Uwe Carstensen, Susanne J. Jekat, Ralf Klabunde. Pages PDF. Request PDF on ResearchGate | On Jan 1, , Carstensen and others published Computerlinguistik und Sprachtechnologie: Eine Einführung | Academic.
|Language:||English, Portuguese, German|
|Genre:||Business & Career|
|ePub File Size:||22.88 MB|
|PDF File Size:||11.59 MB|
|Distribution:||Free* [*Registration needed]|
Request PDF on ResearchGate | Methoden | In diesem Kapitel zu den Methoden der (Computerlinguistik und Sprachtechnologie. Eine Einführung.). This ebooks Computerlinguistik Und Sprachtechnologie Eine Einfuhrung contains all the information and a detailed explanation about Computerlinguistik Und. Computerlinguistik und. Sprachtechnologie Prof. Dr. Udo Hahn. Lehrstuhl für Computerlinguistik .. raudone.info
Plug latent structures and play coreference resolution. Visual error analysis for entity linking. Analyzing and visualizing coreference resolution errors. Graph-based coherence modeling for assessing readability.
Event extraction as frame-semantic parsing. A latent variable model for discourse-aware concept and entity disambiguation. A rule-based system for end-to-end bridging resolution. Recall error analysis for coreference resolution. Dependency parsing with latent refinements of part-of-speech tags. Unsupervised coreference resolution by utilizing the most informative relations. Unsupervised training set generation for automatic acquisition of technical terminology in patents.
Scoring coreference partitions of predicted mentions: A reference implementation. Normalized entity graph for computing local coherence. Multi-document summarization using bipartite graphs.
Transforming Wikipedia into a large scale multilingual concept network. Artificial Intelligence, Graph-based local coherence modeling.
PDF Sebastian Martschat Multigraph clustering for unsupervised coreference resolution. Global inference for bridging anaphora resolution.
Cascading collective classification for bridging anaphora recognition using a rich linguistic feature set. Multimedia information seeking through search and hyperlinking. Collective classification for fine-grained information status.
Jointly disambiguating and clustering concepts and entities with Markov logic. Local and global context for supervised and unsupervised metonymy resolution. A multigraph model for coreference resolution. Concept-based selectional preferences and distributional representations from Wikipedia articles. Taxonomy induction based on a collaboratively built knowledge repository. Unrestricted coreference resolution via global hypergraph partitioning.
Fine-grained sentiment analysis with structural features. CoSyne: A framework for multilingual content synchronization of Wikis. Modeling spatial knowledge for generating verbal and visual route directions. End-to-end coreference resolution via hypergraph partitioning. Evaluation metrics for end-to-end coreference resolution systems. PDF Viola Ganter Detecting vagueness in two languages and two domains.
WikiNet: A very large scale multi-lingual concept network. Classification of semantic relations between nominals. Language Resources and Evaluation, 43 2 DOI Michael Strube Carstensen, C. Ebert, C. Endriss, S. Jekat, R. Klabunde, and H. Finding hedges by chasing weasels: Hedge detection using Wikipedia tags and shallow linguistic features.
Combining collocations, lexical and encyclopedic knowledge for metonymy resolution. In some languages, grammatical gender.
The same semantic relations link structurally different realizations of concepts. Linguistic Issues in Language Technology, 2 3 pages. Summarizing with encyclopedic knowledge.
Creating an annotated corpus for generating walking directions. Tree linearization in English: Improving language model based approaches.
Company-oriented extractive summarization of financial news. Generating update summaries with spreading activation. Sentence fusion via dependency graph compression. PDF Vivi Nastase Topic-driven multi-document summarization with encyclopedic knowledge and activation spreading.
Decoding Wikipedia category names for knowledge acquisition. WikiTaxonomy: A large scale knowledge resource. PDF Short paper. BART: A modular toolkit for coreference resolution. Dependency tree based sentence compression. Distinguishing between instances and classes in the Wikipedia taxonomy. Acquiring a taxonomy from the German Wikipedia.
A three-stage disfluency classifier for multi-party dialogues. Parameters for topic boundary detection in multi-party dialogues. Knowledge sources for bridging resolution in multi-party dialog. Unsupervised all-words word sense disambiguation with grammatical dependencies. The Telling Tail: Signals of success in electronic negotiation texts. Knowledge derived from Wikipedia for computing semantic relatedness.
Journal of Artificial Intelligence Research, The German Vorfeld and local coherence.
Publications and Papers
Journal of Logic, Language and Information, 16 4 Content analysis through the machine learning mill. Group Decision and Negotiations, 16 4 Michael Strube Corpus-based and machine learning approaches to coreference resolution. Schwarz-Friesel, M. Consten, and M.
Shop Computerlinguistik Und Sprachtechnologie: Eine Einführung (German Edition)
Cognitive, formal and applied approaches to anaphoric reference, pages E-VIEW-alation — a large-scale evaluation study of association measures for collocation identification. In Electronic lexicography in the 21st century.
Proceedings of the eLex conference, pages —, Leiden, The Netherlands. Reliable measures of syntactic and lexical complexity: The case of Iris Murdoch.
Large-scale evaluation of dependency-based DSMs: Are they worth the effort? Translation inference across dictionaries via a combination of graph-based methods and co-occurrence statistics. An n-gram based approach to the automatic diagnosis of alzheimer's disease from spoken language. EmpiriST A shared task on the automatic linguistic annotation of computer-mediated communication and web corpora. The CogALex-V shared task on the corpus-based identification of semantic relations.
An analysis of perplexity to reveal the effects of Alzheimer's disease on language. Ziggurat: A new data model and indexing format for large annotated text corpora. Towards a better understanding of Burrows's Delta in literary authorship attribution. KLUEless: Polarity classification and association. Towards a Firthian notion of collocation. Abel and L. Lemnitzer eds.
A weakly supervised multivariate approach to the study of language variation. Szmrecsanyi and B. De Gruyter, Berlin. Distributional semantics in R with the wordspace package.
NaDiR: Naive distributional response generation. Contrasting syntagmatic and paradigmatic relations: Insights from distributional semantic models.Clocksin, William F. In case a , the part of the evaluation that concerns the linguistic quality of the TT might be ignored beyond the degree where the TT is roughly comprehensible. The last two objectives accord with strategic goals set out in ZHW's revised teaching policy aimed at reducing contact hours and increasing the proportion of time students spend on group-work and self-study.
Consten, and M. Hartmann Ed. Auf den Themenbereich lexikalische Semantik wird nur am Rande eingegangen. A study of sentiment and gender influence on negotiation outcome in electronic negotiations. Shallow Processing with Unification and Typed Feature Structures SProUT platform for development of multilingual shallow text processing and information extraction systems.