@article{kluegl2013exploiting,
  abstract = {Conditional Random Fields (CRF) are popular methods for labeling unstructured or textual data. Like many machine learning approaches, these undirected graphical models assume the instances to be independently distributed. However, in real-world applications data is grouped in a natural way, e.g., by its creation context. The instances in each group often share additional structural consistencies. This paper proposes a domain-independent method for exploiting these consistencies by combining two CRFs in a stacked learning framework. We apply rule learning collectively on the predictions of an initial CRF for one context to acquire descriptions of its specific properties. Then, we utilize these descriptions as dynamic and high quality features in an additional (stacked) CRF. The presented approach is evaluated with a real-world dataset for the segmentation of references and achieves a significant reduction of the labeling error.},
  author = {Kluegl, Peter and Toepfer, Martin and Lemmerich, Florian and Hotho, Andreas and Puppe, Frank},
  interhash = {9ef3f543e4cc9e2b0ef078595f92013b},
  intrahash = {fbaab25e96dd20d96ece9d7fefdc3b4f},
  journal = {Mathematical Methodologies in Pattern Recognition and Machine Learning Springer Proceedings in Mathematics & Statistics},
  pages = {111-125},
  title = {Exploiting Structural Consistencies with Stacked Conditional Random Fields},
  volume = 30,
  year = 2013
}

@article{Anicich01112014,
  abstract = {Interpreting scholarly contributions solely on the basis of the number, and not nature, of citations is inherently flawed because contradictory as well as confirmatory findings feed into the same metric, capturing popularity at the expense of precision. I propose a citation and indexing procedure that would conveniently integrate information about research trends while imposing minimal burden on the producers and consumers of research. Under the proposed system, citations appearing in the reference list of research reports would be superscripted with letters corresponding to one of the following six categories: references to findings that are Consistent with the current findings, are Replicated by the current findings, are Inconsistent with the current findings, Failed to be replicated by the current findings, were used to build Theory, or were used to cite Methodologies. I explain how the resulting CRIF-TM data could be summarized and perpetually updated by an online indexing service. I provide an example to demonstrate how these superscripts could be conveniently and unobtrusively presented in the reference list of forthcoming articles. Finally, I examine the anticipated benefits, limitations, and implementation challenges of the proposed citation and indexing procedure.},
  author = {Anicich, Eric M.},
  doi = {10.1177/1745691614549772},
  eprint = {http://pps.sagepub.com/content/9/6/682.full.pdf+html},
  interhash = {af5e16af5f2861d1e53f02d8e58cf221},
  intrahash = {ead9a503ae90b7f74d16739d7e813454},
  journal = {Perspectives on Psychological Science},
  number = 6,
  pages = {682-691},
  title = {What Lies Within: Superscripting References to Reveal Research Trends},
  url = {http://pps.sagepub.com/content/9/6/682.abstract},
  volume = 9,
  year = 2014
}

@inproceedings{toepfer2011segmentation,
  author = {Toepfer, Martin and Kluegl, Peter and Hotho, Andreas and Puppe, Frank},
  booktitle = {Workshop Notes of the LWA 2011 - Learning, Knowledge, Adaptation},
  interhash = {3bd61ad3f9b4f1e221e79ecb3b4cae39},
  intrahash = {b707fa6ddf5b3010827868ecebc60d6a},
  title = {Segmentation of References with Skip-Chain Conditional Random Fields for Consistent Label Transitions},
  url = {http://ki.informatik.uni-wuerzburg.de/papers/pkluegl/2011-LWA-SkYp.pdf},
  year = 2011
}

@inproceedings{2010-KI-KHP,
  abstract = {The accurate extraction of scholarly reference information from scientific publications is essential for many useful applications like BibTeX  management systems or citation analysis. Automatic extraction methods suffer from the heterogeneity of reference notation, no matter wether the extraction model was handcrafted or learnt from labeled data. However, references of the same paper or journal are usually homogeneous. We exploit this local consistency with a novel approach. Given some initial information from such a reference section, we try to derived generalized patterns. These patterns are used to create a local model of the current document. The local model helps to identify errors and to improve the extracted information incrementally during the extraction process. Our approach is implemented with handcrafted transformation rules working on a meta-level being able to correct the information independent of the applied layout style. The experimental results compete very well with the state of the art methods and show an extremely high performance on consistent reference sections. },
  author = {Kluegl, Peter and Hotho, Andreas and Puppe, Frank},
  booktitle = {KI 2010: Advances in Artificial Intelligence, 33rd Annual German Conference on AI},
  editor = {Dillmann, Rüdiger and Beyerer, Jürgen and Hanebeck, Uwe D. and Schultz, Tanja},
  interhash = {b6a5b2a32346b60eac912ee96e681dce},
  intrahash = {174791d9668705cbf0052224694f5366},
  isbn = {978-3-642-16110-0},
  pages = {40-47},
  publisher = {Springer},
  series = { LNAI 6359},
  title = {Local Adaptive Extraction of References},
  url = {http://ki.informatik.uni-wuerzburg.de/papers/pkluegl/2010-KI-LAER.pdf},
  year = 2010
}

@inproceedings{pm04accurate,
  author = {Peng, Fuchun and McCallum, Andrew},
  booktitle = {HLT-NAACL},
  ee = {http://acl.ldc.upenn.edu/hlt-naacl2004/main/pdf/176_Paper.pdf},
  interhash = {8f9ef6b359fef3bd08bfed653fe1bb55},
  intrahash = {8d04bc19e470fe4b98e15a27a1e6e7e9},
  pages = {329-336},
  title = {Accurate Information Extraction from Research Papers using Conditional Random Fields},
  url = {http://www.cs.umass.edu/~mccallum/papers/hlt2004.pdf},
  year = 2004
}