Deutsches Forschungszentrum für Künstliche Intelligenz

Language Technology Lab

Ulrich Schäfer
my Xing profile (members only)

View Ulrich  Schaefer's profile on LinkedIn

Ulrich Schäfer

Dr.-Ing., Dipl.-Inform., Senior Engineer, Project Manager
Hybrid Natural Language Processing Evangelist

Campus D 3 1, Room C 1.24
German Research Center for Artificial Intelligence (DFKI) GmbH
Language Technology Lab
Stuhlsatzenhausweg 3
D-66123 Saarbrücken, Germany
Phone: +49 681 85775-5154
Fax: +49 681 85775-5338
Email: ulrich.schaefer@dfki.de


About me

I am a researcher and IT professional with broad, long-term experience in research, software development and consulting for industry and the European institutions. My current research focus lies in natural language processing: text mining, multilingual information extraction, NLP for scientific publication analysis, NLP software architectures, question answering, semantic search in digital libraries, knowledge representation, knowledge management, semantic web, deep and hybrid parsing. I like Java, Python, XML, Linux and open source technologies.


News


Research Projects


Systems

ACL Anthology Searchbench
  • ACL Anthology Searchbench - Semantic, Fulltext and Bibliographic Search in more than 25,000 papers of the ACL Anthology (try the system here!)
    The Searchbench is a web application combining sentence-semantic search (statements search) with fulltext, terminology and bibliographic search in scholarly papers. The system works domain-independently: even domain terminology ('topics') is extracted fully automatically from collections and individual papers. The statements search helps finding information more precisely. Users can specify subject, predicate and object of sentences expected to be found in the papers, also with only parts of the sentence structure given. The Searchbench can find similar statements, abstract from passive voice, and optionally exclude negated statements or synonym predicates. Search results are displayed in the original PDF and may be emailed or bookmarked. The semantic statements search can also be used as an open online domain term glossary: sample query for dependency parsing. A graphical citation browser helps exploring related work by displaying citation sentence information in the graph. By clicking on nodes or edges, the original citation context can be viewed in the PDF. Altogether, the system is meant to be used as a workbench for search, therefore the name Searchbench.
  • Graphical Citation Browser for the ACL Anthology. Try the system here (sample link)!
  • Scientist's Workbench - Semantic Search and Typed Citation-based Visual Navigation in Scientific Papers
  • SProUT - Shallow Processing with Unification and Typed Feature Structures
  • Heart of Gold - Middleware for Combining Deep and Shallow Natural Language Processing Components

Publications

mostly openly accessible [BibTeX file of all publications] [DFKI's] [LT Lab's list of publications] [DBLP] [ACM] [CSB] [CiteseerX] [ACL Anthology Searchbench] [Google Scholar Citations] [DBLP Visualization]

2013

2012

2011

2010

2008

2007

2006

2005

2004

2003

2002 and earlier


Collaborations

DELPH-IN
  • DELPH-IN (Deep Linguistic Processing with HPSG) - Research sites world-wide have joined forces in a collaborative effort aimed at deep linguistic processing of human language. The goal is the combination of linguistic and statistical processing methods for getting at the meaning of texts and utterances.
  • DELPH-IN wiki

Lectures & Seminars


Courses

ESSLLI'09

Program Committees


Supervised Theses


Misc

SProUTomat
  • SProUTomat - a tool for daily automatically compiling, testing and evaluating SProUT software and lingware (anno 2005).
  • FS2LaTeX - a tool for typesetting SProUT grammars, typed feature structures, RMRS structures (anno 2004).
  • TDL mode for emacs (anno 1993).

last modification 2013-02-21