Abstract
This paper describes the basic concepts and features of the Langusta system. Langusta is a natural language processing environment embedded in a graph database. The paper presents a rule-based syntactic parsing system for the Polish language using various linguistic resources, including those containing semantic information. The advantages of this approach are directly related to the deployment of the graph paradigm, in particular to the assumption, that rules describing the syntax of the Polish language are valid queries in a graph database query language (Cypher).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
- 3.
Apache TinkerPop Project is most known for providing a set of interfaces that graph databases that database vendors can implement (Blueprints) to get all the features of the rest of the TinkerPop stack (Pipes, Gremlin, Frames, Rexster, Furnace) where each part of the stack provides a specific function in supporting graph−based application development; http://tinkerpop.apache.org/.
- 4.
Java types description: https://docs.oracle.com/javase/tutorial/java/nutsandbolts/datatypes.html.
- 5.
Translation to English: “Young girls run.”.
- 6.
The list intersection operator *= is not supported by the implementation of Cypher in the Neo4j database. The interpretation is: false if and only if the list is empty.
- 7.
Correspondence between WHERE expression in Langusta rule and unify operator in SPEJD rule is limited to condition component of unify operator. Application of Langusta rule rejects no interpretation.
- 8.
Correspondence between semantic of group action in SPEJD rule and consequence of Langusta rule application seems to be very strong, obviously excluding capability of ambiguity representation.
- 9.
Langusta supports the handling of word order inversion which is common in the Polish language which is a synthetic language. Through this mechanism the number of rules for parsing the corresponding expressions in normal and inverted order is not doubled. The use of mechanism is limited to rules which match 2 Word nodes. That means that in Langusta system, the expression “dziewczyny młode” will be parsed by the same rule (although certainly not by the same query). To apply the a given rule to the inverted word order it suffices to pass in the appropriate InversionRate value in the environment, i.e. the value of the weight for the rule which tries to perform matching using inverted order of of matching nodes.
- 10.
Phrases “bottle of gasoline”, “sacks for leaves” as instances of prepositional phrases: “container of/for something”. “Bottle” and “sack” are hyponyms of “container” and inherit its valency features.
- 11.
When the MATCH clause contains more than one path, Langusta selects the first one as the matching path by default. The unnamed and undirected relationships between the nodes on this path are labelled :follows and directed from left to right.
- 12.
To increase ease of use of the plWordNet dictionary, the rules work with the transitive closure of the WordNet graph, traversing the hyponymy relation edges, taking into account transition through synset groups, i.e. if a lexical unit: lu1 is a hyponyme of a lexical unit lu2, then all the lexical units sharing the same synset group with lu1 are hyponymes of all lexical units sharing a synset group with lu2.
- 13.
Poliqarp, similary to SPEJD, based its syntax on the formalism CQP derived from the project CWB − The IMS Open Corpus Workbench (http://cwb.sourceforge.net/).
- 14.
Poliqarp, similary to SPEJD, is was used as a part of NKJP project.
References
Buczyński, A., Przepiórkowski, A.: Demo: an open source tool for partial parsing and morphosyntactic disambiguation. In: Proceedings of LREC 2008 (2008)
Dipper, S.: Stand-off representation and exploitation of multi-level linguistic annotation. In: Proceedings of Berliner XML Tage 2005 (BXML 2005), pp. 39–50, Berlin (2005)
Graliński, F., Jassem, K., Junczys-Dowmunt, M.: PSI-Toolkit: Natural language processing pipeline. Computational Linguistics – Applications. Springer, Heidelberg (2012)
Ide, N., Suderman, K.: GrAF: a graph-based format for linguistic annotations. In: Proceedings of the Linguistic Annotation Workshop, pp. 1–8. Czech Republic, Prague (2007)
Joshi, A.K., Schabes, Y.: Tree-adjoining grammars. In: Handbook of Formal Languages, vol. 3, pp. 69–123. Springer-Verlag New York, Inc., New York (1997). ISBN:3–540-60649-1
Negnevitsky, M.: Artificial Intelligence: A Guide to Intelligent Systems. Addison-Wesley Longman Publishing Co., Inc., Boston (2001)
Maziarz, M., Piasecki, M., Szpakowicz, S.: Approaching plWordNet 2.0. In: Proceedings of the 6th Global Wordnet Conference. Matsue, Japan (2012)
Mazur, P.: Text segmentation in polish. In: Proceedings of the 5th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 43–48, 8–10 September 2005, Wroclaw, Poland (2005)
Mihalcea, R., Radev, D.: Graph-Based Natural Language Processing and Information Retrieval. Cambridge University Press, Cambridge (2011)
Pęzik, P.: Indexed graph databases for querying rich TEI annotation (2013). http://digilab2.let.uniroma1.it/teiconf2013/wp-content/uploads/2013/09/Pezik.pdf
Przepiórkowski, A.: Powierzchniowe przetwarzanie języka polskiego. Akademicka Oficyna Wydawnicza EXIT, Warsaw (2008)
Przepiórkowski, A., Bańko, M., Górski, R.L., Lewandowska-Tomaszczyk, B. (eds.): Narodowy Korpus Języka Polskiego. Wydawnictwo Naukowe PWN, Warsaw (2012)
Przepiórkowski, A., Bański, P.: Which XML standards for multilevel corpus annotation? In: Proceedings of the 4th Language & Technology Conference, Poznań, Poland (2009)
Przepiórkowski, A., Buczyński, A.: Shallow parsing and disambiguation engine. In: Vetulani, Z. (ed.) Proceedings of the 3rd Language & Technology Conference, Poznań, Poland, pp. 340–344 (2007)
Przepiórkowski, A., Hajnicz, E., Patejuk, A., Woliński, M., Skwarski, F., Świdziński M.: Walenty: Towards a comprehensive valence dictionary of Polish. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014, pp. 2785–2792, Reykjavík, Iceland. ELRA (2014)
Robinson, I., Webber, J., Eifrem, E.: Graph Databases. O’Reilly Media, Massachusetts (2013)
Rudolf, M., Świdziński, M.: Automatic utterance boundaries recognition in large Polish text corpora. In: Kłopotek, M.A., Wierzchoń, S.T., Trojanowski, K. (eds.) Intelligent Information Processing and Web Mining. Advances in Soft Computing, vol. 25, pp. 247–256. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-39985-8_26
Shi, C., Verhagen, M., Pustejovsky, M.: A conceptual framework of online natural language processing pipeline application. In: Proceedings of the Workshop on Open Infrastructures and Analysis Frameworks for HLT, pp. 53–59, Dublin, Ireland, 23 August (2014)
Strauch, Ch.: NoSQL Databases (2011). http://www.christof-strauch.de/nosqldbs.pdf
Szpakowicz, S.: Automatyczna analiza składniowa polskich zdań pisanych. Praca doktorska (promotor Waligórski S.), Instytut Informatyki UW (1978)
Świdziński, M.: Gramatyka formalna języka polskiego, “Rozprawy Uniwersytetu Warszawskiego”, t. 349, Warsaw (1992)
Wilson, J.R.: Introduction to Graph Theory, 4th edn. Addison Wesley, Reading (1996)
Woliński, M., Miłkowski, M., Ogrodniczuk, M., Przepiórkowski, A., Szałkiewicz, Ł.: PoliMorf: a (not so) new open morphological dictionary for Polish. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation, LREC 2012, pp. 860–864, Istanbul, Turkey. ELRA (2012)
Woliński, M., Przepiórkowski, A.: Projekt anotacji morfosynktaktycznej korpusu języka polskiego. Prace IPI PAN 938, grudzień 2001 (2001)
Wood, P.T.: Query languages for graph databases. ACM SIGMOD Rec. 41(1), 50–60 (2012)
Zeldes, A., Ritz, J., Lüdeling, A., Chiarcos, C.: ANNIS: a search tool for multi-layer annotated corpora. In: Proceedings of Corpus Linguistics 2009, Liverpool, 20–23 July, 2009
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Posiadała, J., Czaja, H., Szczechla, E., Susicki, P. (2018). Parsing of Polish in Graph Database Environment. In: Vetulani, Z., Mariani, J., Kubis, M. (eds) Human Language Technology. Challenges for Computer Science and Linguistics. LTC 2015. Lecture Notes in Computer Science(), vol 10930. Springer, Cham. https://doi.org/10.1007/978-3-319-93782-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-93782-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-93781-6
Online ISBN: 978-3-319-93782-3
eBook Packages: Computer ScienceComputer Science (R0)