Caroline Sporleder

I'm currently a postdoc in the MITCH (Mining for Information in Texts from the Cultural Heritage) project. MITCH is a joint project of the ILK research group at the University of Tilburg and Naturalis, the Dutch National Museum of Natural History, in Leiden. The project is funded by NWO as part of the CATCH (Continuous Access to Cultural Heritage) programme.

Before coming to Tilburg, I was at the University of Edinburgh from where I obtained a PhD in Informatics. My thesis was concerned with the automatic construction of lexical inheritance hierarchies using machine learning techniques. After my PhD I stayed in Edinburgh for a 2-year postdoc project on automatic discourse processing.

My first degree was an MA in Linguistics/Computational Linguistics, English and History from the University of Bielefeld, where I was affiliated with the Computational Linguistics and Spoken Language Group.

Publications:

• Caroline Sporleder and Alex Lascarides.   "Using Automatically Labelled Examples to Classify Rhetorical Relations: An Assessment", to appear in Natural Language Engineering.
  [pdf]   (preprint)


• Caroline Sporleder.   "Manually vs. Automatically Labelled Data in Discourse Relation Classification. Effects of Example and Feature Selection", to appear in LDV Forum.
  [pdf]   (preprint)


• Caroline Sporleder and Mirella Lapata.   "Broad Coverage Paragraph Segmentation across Languages and Domains", ACM Transactions in Speech and Language Processing, 3:2, 1-35, July 2006.
  pdf]   (preprint)

• Sander Canisius and Caroline Sporleder.   "Bootstrapping Information Extraction from Field Books", Proceedings of EMNLP-CoNLL 2007, Prague, Czech Republic, June 28-30, 2007.
  [pdf]


• Iris Hendrickx, Roser Morante, Caroline Sporleder, and Antal van den Bosch.   "Machine learning of semantic relations with shallow features and almost no data", Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval 2007), Prague, Czech Republic, June 23-24, 2007.
  [pdf]


• Sander Canisius and Caroline Sporleder.   "Learning to Segment and Label Semi-Structured Documents with Little or No Supervision", Proceedings of Benelearn 2007, Amsterdam, The Netherlands, May 14-15, 2007.
  [pdf]


• Antal van den Bosch, Caroline Sporleder, Marieke van Erp, and Steve Hunt.  " Automatic Techniques for Generating and Correcting Cultural Heritage Collection Metadata", Digital Humanities 2007, Urbana-Champaign, USA, June 4-8, 2007.
  [html]   (reviewed abstract)


• Caroline Sporleder, Marieke van Erp, Tijn Porcelijn and Antal van den Bosch.   "Correcting 'Wrong-Column' Errors in Text Databases.", Proceedings of the Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn-06), pp. 49-56, Ghent, Belgium, 2006.
  [pdf]


• Caroline Sporleder, Marieke van Erp, Tijn Porcelijn and Antal van den Bosch.   "Spotting the 'Odd-one-out': Data-Driven Error Detection and Correction in Textual Databases.", Proceedings of the EACL 2006 Workshop on Adaptive Text Extraction and Mining (ATEM-06), pp. 41-48, Trento, Italy, 2006.
  [pdf]


• Caroline Sporleder, Marieke van Erp, Tijn Porcelijn, Antal van den Bosch and Pim Arntzen.   "Identifying Named Entities in Text Databases from the Natural History Domain", Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC-06), pp. 1742-1745, Genoa, Italy, 2006.
  [pdf]


• Caroline Sporleder and Mirella Lapata.   "Discourse Chunking and its Application to Sentence Compression", Proceedings of the 2005 Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP-05), Vancouver, Canada, 2005.
  [pdf]


• Caroline Sporleder and Alex Lascarides.   "Exploiting Linguistic Cues to Classify Rhetorical Relations", Proceedings of Recent Advances in Natural Language Processing (RANLP-05), pp. 532-539, Borovets, Bulgaria, 2005. (RANLP-2005 Young Researcher Award)
  [pdf]


• Caroline Sporleder and Mirella Lapata.   "Automatic Paragraph Identification: A Study across Languages and Domains", Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-04), pp. 72-79, Barcelona, Spain, 2004.
  [pdf]
  
• Caroline Sporleder and Alex Lascarides.   "Combining Hierarchical Clustering and Machine Learning to Predict High-Level Discourse Structure", Proceedings of the 20th International Conference on Computational Linguistics (COLING-04), pp. 43-49, Geneva, Switzerland, 2004.
  [ps]
  
• Caroline Sporleder.   "Combining Machine Learning and Set-Theory to Infer Inheritance Hierarchies", Beiträge zur 7. Konferenz zur Verarbeitung Natürlicher Sprache (KONVENS-04), pp. 193-200, Vienna, Austria, 2004.
  [ps]
  
• Caroline Sporleder.   "Learning Lexical Inheritance Hierarchies with Maximum Entropy Models", Workshop on Machine Learning Approaches in Computational Linguistics, ESSLLI 2002, Trento, Italy, 5-16 August 2002.
  [ps]
  
  
• Caroline Sporleder.   "Machine Learning of Lexical Inheritance Hierarchies: Linguistic Plausibility vs. Minimal Redundancy" Proceedings of the Student Research Workshop at the 40th ACL, Philadelphia, USA, 6-12 July 2002.


• Caroline Sporleder.   "A Galois Lattice based Approach to Lexical Inheritance Learning", ECAI 2002 Workshop on Machine Learning and Natural Language Processing for Ontology Engineering (OLT2002), Lyon, France, July 22-23 2002.


• Caroline Sporleder.   "Some Experiments on Lexical Inheritance Hierarchy Learning", Proceedings of TaCoS 2002, Potsdam, Germany, 6-9 June 2002.


• Harald Lüngen and Caroline Sporleder.   "Automatic Induction of Lexical Inheritance Hierarchies", Multilingual Corpora: Codierung, Struktur, Analyse. 11 Jahrestagung der Gesellschaft für Linguistische Datenverarbeitung (GLDV-99), pp. 42-52, Frankfurt a.M., Germany, 1999.
  [ps]

• Caroline Sporleder, Marieke van Erp, Tijn Porcelijn, Antal van den Bosch, Pim Arntzen and Erik van Nieukerken.   Cleaning and Enriching Research Data on Reptiles and Amphibians. The MITCH Pilot Project and "nulmeting". Technical Report, ILK 06-01, Tilburg University, 2006.
  [pdf]

• Caroline Sporleder.   Discovering Lexical Generalisations. A Supervised Machine Learning Approach to Inheritance Hierarchy Construction. PhD Thesis, School of Informatics, University of Edinburgh, 2004.
  [ps]


• Caroline Sporleder.   Learning Lexical Generalisations. An Operational Evaluation of Current Machine Learning Methods. MA Thesis, Universität Bielefeld 1999.
  [ps]


• Caroline Sporleder.   Interfacing Natural Language Generation and Speech Synthesis: A Topic-Comment Mark-Up for ILEX 2.0. MSc Thesis, University of Edinburgh 1997.