Hoppa till huvudinnehåll

BibTeX

@inProceedings{ahlberg-etal-2016-sprakbanken's-246063,
	title        = {Språkbanken’s Open Lexical Infrastructure},
	abstract     = {Karp is an open lexical infrastructure and a web based tool for searching, exploring and developing lexical resources. Språkbanken currently hosts a number of lexicons in Karp and on-going work aims at broadening the type of resources that can be developed in the system. This abstract gives a short overview of Karp's basic functionality, and describes some current projects and on-going work.},
	booktitle    = {SLTC 2016. The Sixth Swedish Language Technology Conference. Umeå University, 17-18 November, 2016},
	author       = {Ahlberg, Malin and Borin, Lars and Forsberg, Markus and Olsson, Olof and Schumacher, Anne and Uppström, Jonatan},
	year         = {2016},
}

@inProceedings{ahlberg-etal-2016-karp-246072,
	title        = {Karp: Språkbanken’s Open Lexical Infrastructure},
	booktitle    = {Globalex 2016, May 24, Portorož, Slovenia},
	author       = {Ahlberg, Malin and Borin, Lars and Forsberg, Markus and Olsson, Olof and Schumacher, Anne and Uppström, Jonatan},
	year         = {2016},
}

@article{adesam-etal-2016-sprakteknologi-237884,
	title        = {Språkteknologi för svenska språket genom tiderna},
	abstract     = {Språkbanken, the Swedish Language Bank, is a language technology research unit at the Department of Swedish, University of Gothenburg. We develop language resources – such as corpora, lexical resources, and analytical tools – for all variants of Swedish, from Old Swedish laws to present-day social media. Historical texts offer exciting theoretical and methodological challenges for language technology because they often defy the assumption inherent in most automatic analysis tools that the texts contain a standardized written language. In this article, we describe our ongoing work on the development of annotated historical corpora, as well as our efforts on linking various resources (both corpora and lexical resources).
This research advances the state of the art of language technology as well as enables new research for scholars in other disciplines.},
	journal      = {Kungliga Skytteanska Samfundets Handlingar},
	author       = {Adesam, Yvonne and Ahlberg, Malin and Andersson, Peter and Borin, Lars and Bouma, Gerlof and Forsberg, Markus},
	year         = {2016},
	volume       = {76},
	number       = {Studier i svensk språkhistoria 13},
	pages        = {65--87},
}

@inProceedings{cap-etal-2016-sword-254388,
	title        = {SWORD: Towards Cutting-Edge Swedish Word Processing},
	abstract     = {Despite many years of research on Swedish language technology, there is still no well-documented standard for Swedish word processing covering the whole spectrum from low-level tokenization to morphological analysis and disambiguation. SWORD is a new initiative within the SWE-CLARIN consortium aiming to develop documented standards for Swedish word processing. In this paper, we report on a pilot study of Swedish tokenization, where we compare the output of six different tokenizers on four different text types.  For one text type (Wikipedia articles), we also compare to the tokenization produced by six manual annotators.},
	booktitle    = {Proceedings of the Sixth Swedish Language Technology Conference (SLTC) Umeå University, 17-18 November, 2016},
	author       = {Cap, Fabienne and Adesam, Yvonne and Ahrenberg, Lars and Borin, Lars and Bouma, Gerlof and Forsberg, Markus and Kann, Viggo and Östling, Robert and Smith, Aaron and Wirén, Mats and Nivre, Joakim},
	year         = {2016},
}

@inProceedings{borin-etal-2016-sparv-246053,
	title        = {Sparv: Språkbanken’s corpus annotation pipeline infrastructure},
	abstract     = {Sparv is Språkbanken's corpus annotation pipeline infrastructure. The easiest way to use the pipeline is from its web interface with a plain text document. The pipeline uses in-house and external tools on the text to segment it into sentences and paragraphs, tokenise, tag parts-of-speech, look up in dictionaries and analyse compounds. The pipeline can also be run using a web API with XML results, and it is run locally at Språkbanken to prepare the documents in Korp, our corpus search tool. While the most sophisticated support is for modern Swedish, the pipeline supports 15 languages.},
	booktitle    = {SLTC 2016. The Sixth Swedish Language Technology Conference, Umeå University, 17-18 November, 2016},
	author       = {Borin, Lars and Forsberg, Markus and Hammarstedt, Martin and Rosén, Dan and Schäfer, Roland and Schumacher, Anne},
	year         = {2016},
}

@inProceedings{forsberg-hulden-2016-deriving-237061,
	title        = {Deriving Morphological Analyzers from Example Inflections},
	abstract     = {This paper presents a semi-automatic method to derive morphological analyzers from a limited number of example inflections suitable for languages with alphabetic writing systems. The system we present learns the inflectional behavior of morphological paradigms from examples and converts the learned paradigms into a finite-state transducer that is able to map inflected forms of previously unseen words into lemmas and corresponding morphosyntactic descriptions. We evaluate the system when provided with inflection tables for several languages collected from the Wiktionary.},
	booktitle    = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC-2016) May 23-28, 2016, Portorož, Slovenia},
	author       = {Forsberg, Markus and Hulden, Mans},
	year         = {2016},
	ISBN         = {978-2-9517408-9-1},
}

@incollection{forsberg-hulden-2016-learning-240208,
	title        = {Learning Transducer Models for Morphological Analysis from Example Inflections},
	abstract     = {In this paper, we present a method to convert morphological inflection tables into unweighted and weighted finite transducers that perform parsing and generation. These transducers model the inflectional behavior of morphological paradigms induced from examples and can map inflected forms of previously unseen word forms into their lemmas and give morphosyntactic descriptions of them. The system is evaluated on several languages with data collected from the Wiktionary.},
	booktitle    = {Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata. Association for Computational Linguistics. August 12, 2016 Berlin, Germany},
	author       = {Forsberg, Markus and Hulden, Mans},
	year         = {2016},
	publisher    = {ACL},
	address      = {Stroudsburg, PA, USA},
	ISBN         = {978-1-945626-13-5 },
	pages        = {42--50},
}