%
% GENERATED FROM https://www.coli.uni-saarland.de
%    by   : anonymous
%    IP   : coli2006.lst.uni-saarland.de
%    at   : Mon, 05 Feb 2024 15:42:51 +0100 GMT
%    
% Selection : Author: Detlef_Prescher
%




@InProceedings{Beil_et_al:2002,
      AUTHOR = {Beil, Franz and Prescher, Detlef and Schmid, Helmut and Schulte im Walde, Sabine},
      TITLE = {Evaluation of the Gramotron Parser for German},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the LREC Workshop: Beyond PARSEVAL, May 29-31},
      ADDRESS = {Las Palmas, Gran Canaria},
      URL = {http://www.dfki.de/~prescher/papers/bib/2002lrec.beil.prescher.schmid.schulte_im_walde.pdf},
      ABSTRACT = {The paper describes an experiment in inside-outside estimation of a lexicalized probabilistic context free grammar for German. Grammar and formalism features which make the experiment feasible are described. Successive models are evaluated on precision and recall of phrase markup consisting of labels for noun chunks and subcategorization frames. Our approach to parsing is a blend of symbolic and stochastic methods where we use evaluation results in both incremental grammar development and validation of selected output to be used in lexical semantic clustering. Our results are that (i) scrambling-style free phrase order, case morphology, subcategorization, and NP-internal gender, number and case agreement can be dealt within a lexicalized probabilistic context-free grammar formalism, and (ii) inside-outside estimation appears to be beneficial, however relies on a carefully built grammar and an evaluation based on carefully selected linguistic criteria. Additionally, we report experiments on overtraining with inside-outside estimation, especially focusing on comparison of the results of mathematical and linguistic evaluations.},
      ANNOTE = {COLIURL : Beil:2002:EGP.pdf}
}

@InProceedings{Carroll_et_al:2002,
      AUTHOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans},
      TITLE = {Introductory pages of the editors},
      YEAR = {2002},
      BOOKTITLE = {Beyond PARSEVAL - Towards Improved Evaluation Measures for Parsing Systems. Workshop at the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 28},
      EDITOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans},
      ADDRESS = {Las Palmas, Gran Canaria, Spain},
      URL = {http://www.dfki.de/dfkibib/publications/docs/intro.ps},
      ANNOTE = {COLIURL : Carroll:2002:IPE.pdf Carroll:2002:IPE.ps}
}

@InProceedings{Carroll_et_al:2002,
      AUTHOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans},
      TITLE = {Introductory pages of the editors},
      YEAR = {2002},
      BOOKTITLE = {Beyond PARSEVAL - Towards Improved Evaluation Measures for Parsing Systems. Workshop at the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 28},
      EDITOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans},
      ADDRESS = {Las Palmas, Gran Canaria, Spain},
      URL = {http://www.dfki.de/dfkibib/publications/docs/intro.ps},
      ANNOTE = {COLIURL : Carroll:2002:IPE.pdf Carroll:2002:IPE.ps}
}

@Book{John_et_al:2002,
      TITLE = {Beyond PARSEVAL - Towards Improved Evaluation Measures for Parsing Systems. Workshop at the 3rd International Conference on Language Resources and Evaluation (LREC-02)},
      YEAR = {2002},
      EDITOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans},
      ADDRESS = {Las Palmas, Gran Canaria, Spain},
      URL = {http://www.cogs.susx.ac.uk/lab/nlp/carroll/papers/beyond-proceedings.pdf},
      ANNOTE = {COLIURL : Carroll:2002:BPT.pdf}
}

@InProceedings{Kiefer_et_al:2002,
      AUTHOR = {Kiefer, Bernd and Krieger, Hans-Ulrich and Prescher, Detlef},
      TITLE = {A Novel Disambiguation Method For Unification-Based Grammars Using Probabilistic Context-Free Approximations},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics (COLING'02), August 24 - September 1},
      ADDRESS = {Taipei, Taiwan},
      URL = {http://www.dfki.de/dfkibib/publications/docs/paper-alternative-font2},
      ABSTRACT = {We present a novel disambiguation method for unificationbased grammars (UBGs). In contrast to other methods, our approach obviates the need for probability models on the UBG side in that it shifts the responsibility to simpler contextfree models, indirectly obtained from the UBG. Our approach has three advantages: (i) training can be effectively done in practice, (ii) parsing and disambiguation of contextfree readings requires only cubic time, and (iii) involved probability distributions are mathematically clean. In an experiment for a midsize UBG, we show that our novel approach is feasible. Using unsupervised training, we achieve 88% accuracy on an exactmatch task.},
      ANNOTE = {COLIURL : Kiefer:2002:NDM.pdf Kiefer:2002:NDM.ps}
}

@InProceedings{Prescher:2001,
      AUTHOR = {Prescher, Detlef},
      TITLE = {Novel Properties and Well-Tried Performance of EM-Based Multivariate Clustering},
      YEAR = {2001},
      BOOKTITLE = {Proceedings of the EuroConference on Recent Advances in Natural Language Processing (RANLP-01), September 5-7},
      PAGES = {216-222},
      ADDRESS = {Tzigov Chark, Bulgaria},
      URL = {http://www.dfki.de/~prescher/papers/bib/2001ranlp.prescher.pdf},
      ABSTRACT = {We present three novel properties for EM-based multivariate clustering: simplified re-estimation formulas, a simple pruning technique, and a novel invariance property preserving the characteristics of the given empirical distribution. Evaluation on two tasks shows: EM-based multivariate clustering models require only twice the storage space of the original sample, and these models yield reliable estimates for unknown data. Moreover we refer to selected experiments showing that EM-based multivariate clustering improves several real-world applications.},
      ANNOTE = {COLIURL : Prescher:2001:NPW.pdf}
}

@TechReport{Prescher:2001_1,
      AUTHOR = {Prescher, Detlef},
      TITLE = {Inside-Outside Estimation Meets Dynamic EM - GOLD},
      YEAR = {2001},
      NUMBER = {RR-01-02},
      ADDRESS = {Saarbrücken},
      TYPE = {Research Report},
      INSTITUTION = {DFKI},
      URL = {http://www.dfki.de/~prescher/papers/bib/2001dfki_report.prescher.pdf},
      ABSTRACT = {It is an interesting fact that most of the stochastic models used by linguists can be interpreted as probabilistic context-free grammars. In this paper, this result will be accompanied by the formal proof that the inside-outside algorithm, the standard training method for probabilistic context-free grammars, can be regarded as a dynamic-programming variant of the EM algorithm. Even if this result is considered in isolation this means that most of the probabilistic models used by linguists are trained by a version of the EM algorithm. However, this result is even more interesting when considered in a theoretical context because the well-known convergence behavior of the inside-outside algorithm has been confirmed by many experiments but it seems that it never has been formally proved. Furthermore, being a version of the EM algorithm, the inside-outside algorithm also inherits the good convergence behavior of EM. We therefore contend that the as yet imperfect line of argumentation can be transformed into a coherent proof.},
      ANNOTE = {COLIURL : Prescher:2001:IOEa.pdf}
}

@InProceedings{Prescher:2001_2,
      AUTHOR = {Prescher, Detlef},
      TITLE = {Inside-Outside Estimation Meets Dynamic EM},
      YEAR = {2001},
      BOOKTITLE = {Proceedings of the 7th International Workshop on Parsing Technologies (IWPT-01), October 17-19},
      PAGES = {241-244},
      ADDRESS = {Beijing, China},
      URL = {http://www.dfki.de/~prescher/papers/bib/2001iwpt.prescher.pdf},
      ABSTRACT = {It is an interesting fact that most of the stochastic models used by linguists can be interpreted as probabilistic context-free grammars. In this paper, this result will be accompanied by the formal proof that the inside-outside algorithm, the standard training method for probabilistic context-free grammars, can be regarded as a dynamic-programming variant of the EM algorithm. Even if this result is considered in isolation this means that most of the probabilistic models used by linguists are trained by a version of the EM algorithm. However, this result is even more interesting when considered in a theoretical context because the well-known convergence behavior of the inside-outside algorithm has been confirmed by many experiments but it seems that it never has been formally proved. Furthermore, being a version of the EM algorithm, the inside-outside algorithm also inherits the good convergence behavior of EM. We therefore contend that the as yet imperfect line of argumentation can be transformed into a coherent proof.},
      ANNOTE = {COLIURL : Prescher:2001:IOEb.pdf}
}

@PhdThesis{Prescher:2002,
      AUTHOR = {Prescher, Detlef},
      TITLE = {EM-basierte maschinelle Lernverfahren für natürliche Sprachen},
      YEAR = {2002},
      NUMBER = {8(1)},
      SERIES = {AIMS Report},
      ADDRESS = {Stuttgart},
      SCHOOL = {Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung (IMS)},
      URL = {http://www.dfki.de/~prescher/papers/bib/2002phd.prescher.pdf},
      ABSTRACT = {This thesis presents the Expectation-Maximization algorithm (EM algorithm, Dempster et al. (1977)) in its practical and theoretical aspects. The EM algorithm is the stochastic basis of many machine learning algorithms for natural language processing. In the theoretical part of this thesis the stochastic basis of linguistics and the formal basis of the EM algorithm is explained. The practical part of this thesis presents a probabilistic clustering method for multivariate linguistic data and stochastic modeling of lexicalized grammars.},
      ANNOTE = {COLIURL : Prescher:2002:EBM.pdf}
}

@InCollection{Schulte im Walde_et_al:2001,
      AUTHOR = {Schulte im Walde, Sabine and Schmid, Helmut and Rooth, Mats and Riezler, Stefan and Prescher, Detlef},
      TITLE = {Statistical Grammar Models and Lexicon Acquisition},
      YEAR = {2001},
      BOOKTITLE = {Linguistic Form and its Computation},
      ADDRESS = {Stanford},
      PUBLISHER = {CSLI Publications},
      URL = {http://www.dfki.de/~prescher/papers/bib/2001csli.schulte_im_walde.schmid.rooth.riezler.prescher.pdf},
      ANNOTE = {COLIURL : Walde:2001:SGM.pdf}
}

@InProceedings{Vintar_et_al:2002,
      AUTHOR = {Vintar, Spela and Buitelaar, Paul and Ripplinger, Bärbel and Sacaleanu, Bogdan and Raileanu, Diana and Prescher, Detlef},
      TITLE = {An Efficient and Flexible Format for Linguistic and Semantic Annotation},
      YEAR = {2002},
      BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31},
      ADDRESS = {Las Palmas, Canary Islands, Spain},
      URL = {http://dfki.de/~paulb/lrec2002.dtd.ps http://www.dfki.de/dfkibib/publications/docs/lrec2002.dtd.final.pdf},
      ABSTRACT = {The paper describes an XML annotation format and tool developed within the MUCHMORE project. The annotation scheme was designed specifically for the purposes of Cross-Lingual Information Retrieval in the medical domain so as to allow both efficient and flexible access to layers of information. We use a parallel English-German corpus of medical abstracts and annotate it with linguistic information (tokenisation, part-of-speech tagging, lemmatisation and decomposition, phrase recognition, grammatical functions) as well as semantic information from various sources. The annotation of medical terms/concepts, semantic types and semantic relations is based on the Unified Medical Language System (UMLS). Additionally, we use EuroWordNet as a general-language resource in annotating word senses and to compare domain-specific and general language use. A major aim of the project is also to complement existing ontological resources by extracting new terms and new semantic relations. We present the annotation scheme, which is conceptually related to stand-off annotation, and describe our tool for automatic semantic annotation.},
      ANNOTE = {COLIURL : Vintar:2002:EFF.pdf Vintar:2002:EFF.ps}
}

@InProceedings{Baldewein_et_al:2004,
      AUTHOR = {Baldewein, Ulrike and Erk, Katrin and Pado, Sebastian and Prescher, Detlef},
      TITLE = {Semantic Role Labelling for Chunk Sequences},
      YEAR = {2004},
      BOOKTITLE = {Proceedings of the CoNLL'04 shared task},
      ADDRESS = {Boston, MA},
      URL = {https://www.coli.uni-saarland.de/~erk/OnlinePapers/conll.ps}
}

@InProceedings{Baldewein_et_al:2004_1,
      AUTHOR = {Baldewein, Ulrike and Erk, Katrin and Pado, Sebastian and Prescher, Detlef},
      TITLE = {Semantic Role Labelling with Similarity-Based Generalization Using EM-based Clustering},
      YEAR = {2004},
      BOOKTITLE = {Proceedings of Senseval'04},
      ADDRESS = {Barcelona},
      URL = {https://www.coli.uni-saarland.de/~erk/OnlinePapers/senseval.ps}
}

@InProceedings{Fissaha_et_al:2003,
      AUTHOR = {Fissaha, S. and Olejnik, D. and Kornberger, R. and Müller, Karin and Prescher, Detlef},
      TITLE = {Experiments in German treebank parsing},
      YEAR = {2003},
      BOOKTITLE = {Text, Speech and Dialogue, 6th International Conference, TSD 2003},
      VOLUME = {2807},
      PAGES = {50-57},
      EDITOR = {Matousek, Václav and Mautner, Pavel},
      ADDRESS = {Ceske Budejovice, Czech Republic},
      PUBLISHER = {Springer}
}