BibTeX

@inProceedings{johansson-2013-training-173587,
	title        = {Training Parsers on Incompatible Treebanks},
	abstract     = {We consider the problem of training a statistical parser in the
situation when there are multiple treebanks available, and these
treebanks are annotated according to different linguistic
conventions. 

To address this problem, we present two simple adaptation methods:
the first method is based on the idea of using a shared feature
representation when parsing multiple treebanks, and the second method
on guided parsing where the output of one parser provides features
for a second one.

To evaluate and analyze the adaptation methods, we train parsers
on treebank pairs in four languages: German, Swedish, Italian, and English.
We see significant improvements for all eight treebanks when training
on the full training sets. However, the clearest benefits are seen when we
consider smaller training sets. Our experiments were carried out with
unlabeled dependency parsers, but the methods can easily be 
generalized to other feature-based parsers.},
	booktitle    = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
	author       = {Johansson, Richard},
	year         = {2013},
	pages        = {127--137},
}

@inProceedings{borin-etal-2013-mining-188846,
	title        = {Mining semantics for culturomics: towards a knowledge-based approach},
	abstract     = {The massive amounts of text data made available through the Google Books digitization project have inspired a new field of big-data textual research. Named culturomics, this field has attracted the attention of a growing number of scholars over recent years. However, initial studies based on these data have been criticized for not referring to relevant work in linguistics and language technology. This paper provides some ideas, thoughts and first steps towards a new culturomics initiative, based this time on Swedish data, which pursues a more knowledge-based approach than previous work in this emerging field. The amount of new Swedish text produced daily and older texts being digitized in cultural heritage projects grows at an accelerating rate. These volumes of text being available in digital form have grown far beyond the capacity of human readers, leaving automated semantic processing of the texts as the only realistic option for accessing and using the information contained in them. The aim of our recently initiated research program is to advance the state of the art in language technology resources and methods for semantic processing of Big Swedish text and focus on the theoretical and methodological advancement of the state of the art in extracting and correlating information from large volumes of Swedish text using a combination of knowledge-based and statistical methods.},
	booktitle    = {2013 ACM International Workshop on Mining Unstructured Big Data Using Natural Language Processing, UnstructureNLP 2013, Held at 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013; San Francisco, CA; United States; 28 October 2013 through 28 October 2013},
	author       = {Borin, Lars and Dubhashi, Devdatt and Forsberg, Markus and Johansson, Richard and Kokkinakis, Dimitrios and Nugues, Pierre},
	year         = {2013},
	ISBN         = {978-1-4503-2415-1},
	pages        = {3--10},
}