lnu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Nilsson, Jens
Publications (10 of 23) Show all publications
Nilsson, J. (2009). Transformation and Combination in Data-Driven Dependency Parcing. (Doctoral dissertation). Växjö: Växjö University Press
Open this publication in new window or tab >>Transformation and Combination in Data-Driven Dependency Parcing
2009 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

This thesis deals with automatic syntactic analysis of natural languagetext, also known as parsing. The parsing approach is data-driven, whichmeans that parsers are constructed by means of machine learning, lookingat training data in the form of annotated natural language sentences. The syntactic framework used in the thesis is dependency-based. Robustness is one of the characteristics of the data-driven approaches investigated here.The overall aim of this thesis is to maintain robustness while increasing accuracy.The content of the thesis falls naturally into two tracks, a transformation track and a combination track. The  rst type of transformation investigatedis called pseudo-projective, because it enables strictly projective dependency parsers to recover non-projective dependency relations. Informally,a non-projective dependency tree contains crossing binary directed relations, when drawn above the sentence. Experimental results show that pseudo-projective transformations can improve accuracy significantly for a range of languages. The second type of transformation aims to facilitate the processing of specific linguistic constructions such as coordination and verb groups. Experimental results again show a positive effect on parsing accuracy for several languages, often greater than for the pseudo-projective transformations. However, the improvement of the transformations dependson the internal structure of the base parser, which is not the case for thepseudo-projective transformations. The combination track compares various approaches for combining data driven dependency parsers, again as a means of improving accuracy. As different parsers have different strengths and weaknesses, making parsers collaborate in order to  nd one single syntactic analysis may result in higher accuracy than any of the syntactic analyzers can produce by itself. The experimental results show that accuracy improves across languages, giventhat appropriate parsers are combined. The thesis ends with an attempt to combine the two tracks, showing that combining parsers with different tree transformations also increases accuracy. Moreover, this experiment indicates that high diversity among a small set of parsers is much more important than a large number of parsers with low diversity.

Place, publisher, year, edition, pages
Växjö: Växjö University Press, 2009. p. 136
Series
Acta Wexionensia, ISSN 1404-4307 ; 183/2009
Keywords
Natural Language Parsing, Dependency Parsing, Tree Transformation
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-6776 (URN)978-91-7636-674-5 (ISBN)
Public defence
2009-10-16, Weber, Växjö universitet, 13:15 (English)
Opponent
Supervisors
Available from: 2010-01-19 Created: 2010-01-18 Last updated: 2018-01-12Bibliographically approved
Nilsson, J. & Nivre, J. (2008). Dependency Parsing by Transformation and Combination. In: 6th International Conference on Natural Language Processing, GoTAL 2008 (pp. 348–359). Springer, Gothenburg, Sweden
Open this publication in new window or tab >>Dependency Parsing by Transformation and Combination
2008 (English)In: 6th International Conference on Natural Language Processing, GoTAL 2008, Springer, Gothenburg, Sweden , 2008, p. 348–359-Conference paper, Published paper (Refereed)
Abstract [en]

This study presents new language and treebank independent

graph transformations that improve accuracy in data-driven dependency parsing. We show that individual generic graph transformations can increase accuracy across treebanks, but especially when they are combined using established parser combination techniques. The combination experiments also indicate that the presumed best way to combine parsers, using the highest scoring parsers, is not necessarily the best approach.

Place, publisher, year, edition, pages
Springer, Gothenburg, Sweden, 2008
Keywords
Inductive Dependency Parsing, Tree Transformations, Parser Combination
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-3884 (URN)
Available from: 2009-01-04 Created: 2009-01-04 Last updated: 2018-01-13Bibliographically approved
Nilsson, J. & Nivre, J. (2008). MaltEval: An Evaluation and Visualization Tool for Dependency Parsing. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC'08). Marrakech, Morocco
Open this publication in new window or tab >>MaltEval: An Evaluation and Visualization Tool for Dependency Parsing
2008 (English)In: Proceedings of the Sixth International Language Resources and Evaluation (LREC'08), Marrakech, Morocco , 2008Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a freely available evaluation tool for dependency parsing, MaltEval (http://w3.msi.vxu.se/users/jni/malteval). It is flexible and extensible, and provides functionality for both quantitative evaluation and visualization of dependency structure. The quantitative evaluation is compatible with other standard evaluation software for dependency structure which does not produce visualization of dependency structure, and can output more details as well as new types of evaluation metrics. In addition, MaltEval has generic support for confusion matrices. It can also produce statistical significance tests when more than one parsed file is specified. The visualization

module also has the ability to highlight discrepancies between the gold-standard files and the parsed files, and it comes with an easy to use GUI functionality to search in the dependency structure of the input files.

Place, publisher, year, edition, pages
Marrakech, Morocco, 2008
Keywords
Dependency Treebank, Evaluation
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-3883 (URN)
Available from: 2009-01-04 Created: 2009-01-04 Last updated: 2018-01-13Bibliographically approved
Hall, J., Nivre, J. & Nilsson, J. (2007). A Hybrid Constituency-Dependency Parser for Swedish. In: Proceedings of the 16th Nordic Conference of Computational Linguistics (NODALIDA) (pp. 284–287).
Open this publication in new window or tab >>A Hybrid Constituency-Dependency Parser for Swedish
2007 (English)In: Proceedings of the 16th Nordic Conference of Computational Linguistics (NODALIDA), 2007, p. 284–287-Conference paper, Published paper (Refereed)
Abstract [en]

We present a data-driven parser that derives both constituent structures and dependency structures, alone or in combination, in one

and the same process. When trained and tested on data from the Swedish treebank Talbanken05, the parser achieves a labeled dependency accuracy of 82% and a labeled bracketing F-score of 75%.

Keywords
dependency parsing, parsing, dependency structures, constituent structures
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-4746 (URN)
Available from: 2007-10-24 Created: 2007-10-24 Last updated: 2018-01-13Bibliographically approved
Nilsson, J., Nivre, J. & Hall, J. (2007). Generalizing Tree Transformations for Inductive Dependency Parsing. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (pp. 968–975). Association for Computational Linguistics
Open this publication in new window or tab >>Generalizing Tree Transformations for Inductive Dependency Parsing
2007 (English)In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Association for Computational Linguistics , 2007, p. 968–975-Conference paper, Published paper (Refereed)
Abstract [en]

Previous studies in data-driven dependency parsing have shown that tree transformations can improve parsing accuracy for specific parsers and data sets. We investigate to what extent this can be generalized across languages/treebanks and parsers, focusing on pseudo-projective parsing, as a way of capturing non-projective dependencies, and transformations used to facilitate parsing of coordinate structures and verb groups. The results indicate that the beneficial effect of pseudo-projective parsing is independent of parsing strategy but sensitive to language or treebank specific properties. By contrast, the construction specific transformations appear to be more sensitive to parsing strategy but have a constant positive effect over several languages.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2007
Keywords
Tree Transformations, Inductive Dependency Parsing, data-driven, treebank, pseudo-projective parsing
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-4747 (URN)
Available from: 2007-10-24 Created: 2007-10-24 Last updated: 2018-01-13Bibliographically approved
Nivre, J., Hall, J., Nilsson, J., Chanev, A., Eryigit, G., Kübler, S., . . . Marsi, E. (2007). MaltParser: A Language-Independent System for Data-Driven Dependency Parsing. Natural Language Engineering, 13(2), 95-135
Open this publication in new window or tab >>MaltParser: A Language-Independent System for Data-Driven Dependency Parsing
Show others...
2007 (English)In: Natural Language Engineering, Vol. 13, no 2, p. 95-135Article in journal (Refereed) Published
Abstract [en]

Parsing unrestricted text is useful for many language technology applications but requires parsing methods that are both robust and efficient. MaltParser is a language-independent system for data-driven dependency parsing that can be used to induce a parser for a new language from a treebank sample in a simple yet flexible manner. Experimental evaluation confirms thatMaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data.

Place, publisher, year, edition, pages
Cambridge University Press, 2007
Keywords
dependency parsing, treebank, machine learning, data-driven, parsing
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-4745 (URN)doi:10.1017/S1351324906004505 (DOI)
Available from: 2007-10-24 Created: 2007-10-24 Last updated: 2018-01-13Bibliographically approved
Hall, J., Nilsson, J., Nivre, J., Eryigit, G., Megyesi, B., Nilsson, M. & Saers, M. (2007). Single Malt or Blended? A Study in Multilingual Parser Optimization. In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007 (pp. 933–939). Association for Computational Linguistics
Open this publication in new window or tab >>Single Malt or Blended? A Study in Multilingual Parser Optimization
Show others...
2007 (English)In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, Association for Computational Linguistics , 2007, p. 933–939-Conference paper, Published paper (Refereed)
Abstract [en]

We describe a two-stage optimization of the MaltParser system for the ten languages in the multilingual track of the CoNLL 2007 shared task on dependency parsing. The first stage consists in tuning a single-parser system for each language by optimizing parameters of the parsing algorithm, the feature model, and the learning algorithm. The second stage consists in building an ensemble system that combines six different parsing strategies, extrapolating from the optimal parameters settings for each language. When evaluated on the official test sets, the ensemble system significantly outperforms the single-parser system and achieves the highest average labeled attachment score.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2007
Keywords
dependency parsing, data-driven, CoNLL
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-4748 (URN)
Available from: 2007-10-24 Created: 2007-10-24 Last updated: 2018-01-13Bibliographically approved
Nivre, J., Hall, J., Kübler, S., McDonald, R., Nilsson, J., Riedel, S. & Yuret, D. (2007). The CoNLL 2007 Shared Task on Dependency Parsing. In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007 (pp. 915–932). Association for Computational Linguistics
Open this publication in new window or tab >>The CoNLL 2007 Shared Task on Dependency Parsing
Show others...
2007 (English)In: Proceedings of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, Association for Computational Linguistics , 2007, p. 915–932-Conference paper, Published paper (Other academic)
Abstract [en]

The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, we define the tasks of the different tracks and describe how the data sets were created from existing treebanks for ten languages. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2007
Keywords
CoNLL, dependency parsing, data-driven, Natural Language Learning
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-4749 (URN)
Available from: 2007-10-24 Created: 2007-10-24 Last updated: 2018-01-13Bibliographically approved
Nilsson, J. (2007). Tree Transformations in Inductive Dependency Parsing. (Licentiate dissertation). Växjö: Matematiska och systemtekniska institutionen
Open this publication in new window or tab >>Tree Transformations in Inductive Dependency Parsing
2007 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

This licentiate thesis deals with automatic syntactic analysis, or parsing, of natural languages. A parser constructs the syntactic analysis, which it learns by looking at correctly analyzed sentences, known as training data. The general topic concerns manipulations of the training data in order to improve the parsing accuracy.

Several studies using constituency-based theories for natural languages in such automatic and data-driven syntactic parsing have shown that training data, annotated according to a linguistic theory, often needs to be adapted in various ways in order to achieve an adequate, automatic analysis. A linguistically sound constituent structure is not necessarily well-suited for learning and parsing using existing data-driven methods. Modifications to the constituency-based trees in the training data, and corresponding modifications to the parser output, have successfully been applied to increase the parser accuracy. The topic of this thesis is to investigate whether similar modifications in the form of tree transformations to training data, annotated with dependency-based structures, can improve accuracy for data-driven dependency parsers. In order to do this, two types of tree transformations are in focus in this thesis.

%This is a topic that so far has been less studied.

The first one concerns non-projectivity. The full potential of dependency parsing can only be realized if non-projective constructions are allowed, which pose a problem for projective dependency parsers. On the other hand, non-projective parsers tend, among other things, to be slower. In order to maintain the benefits of projective parsing, a tree transformation technique to recover non-projectivity while using a projective parser is presented here.

The second type of transformation concerns linguistic phenomena that are possible but hard for a parser to learn, given a certain choice of dependency analysis. This study has concentrated on two such phenomena, coordination and verb groups, for which tree transformations are applied in order to improve parsing accuracy, in case the original structure does not coincide with a structure that is easy to learn.

Empirical evaluations are performed using treebank data from various languages, and using more than one dependency parser. The results show that the benefit of these tree transformations used in preprocessing and postprocessing to a large extent is language, treebank and parser independent.

Place, publisher, year, edition, pages
Växjö: Matematiska och systemtekniska institutionen, 2007
Series
Reports from MSI, ISSN 1650-2647 ; 07002
Keywords
Inductive Dependency Parsing, Dependency Structure, Tree Transformation, Non-projectivity, Coordination, Verb Group
National Category
Language Technology (Computational Linguistics)
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-1205 (URN)
Presentation
2007-01-19, D1136, D-byggnaden, Växjö Universitet, Växjö, 13:15 (English)
Opponent
Supervisors
Available from: 2007-03-21 Created: 2007-03-21 Last updated: 2018-01-13Bibliographically approved
Nilsson, J. (2007). Tree Transformations in Inductive Dependency Parsing. (Licentiate dissertation). Växjö: Matematiska och systemtekniska institutionen
Open this publication in new window or tab >>Tree Transformations in Inductive Dependency Parsing
2007 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

This licentiate thesis deals with automatic syntactic analysis, or parsing, of natural languages. A parser constructs the syntactic analysis, which it learns by looking at correctly analyzed sentences, known as training data. The general topic concerns manipulations of the training data in order to improve the parsing accuracy.

Several studies using constituency-based theories for natural languages in such automatic and data-driven syntactic parsing have shown that training data, annotated according to a linguistic theory, often needs to be adapted in various ways in order to achieve an adequate, automatic analysis. A linguistically sound constituent structure is not necessarily well-suited for learning and parsing using existing data-driven methods. Modifications to the constituency-based trees in the training data, and corresponding modifications to the parser output, have successfully been applied to increase the parser accuracy. The topic of this thesis is to investigate whether similar modifications in the form of tree transformations to training data, annotated with dependency-based structures, can improve accuracy for data-driven dependency parsers. In order to do this, two types of tree transformations are in focus in this thesis.

The first one concerns non-projectivity. The full potential of dependency parsing can only be realized if non-projective constructions are allowed, which pose a problem for projective dependency parsers. On the other hand, non-projective parsers tend, among other things, to be slower. In order to maintain the benefits of projective parsing, a tree transformation technique to recover non-projectivity while using a projective parser is presented here.

The second type of transformation concerns linguistic phenomena that are possible but hard for a parser to learn, given a certain choice of dependency analysis. This study has concentrated on two such phenomena, coordination and verb groups, for which tree transformations are applied in order to improve parsing accuracy, in case the original structure does not coincide with a structure that is easy to learn.

Empirical evaluations are performed using treebank data from various languages, and using more than one dependency parser. The results show that the benefit of these tree transformations used in preprocessing and postprocessing to a large extent is language, treebank and parser independent.

Place, publisher, year, edition, pages
Växjö: Matematiska och systemtekniska institutionen, 2007. p. 84
Series
Reports from MSI, ISSN 1650-2647 ; 07002
Keywords
Inductive Dependency Parsing, Dependency Structure, Tree Transformation, Non-projectivity, Coordination, Verb Group
National Category
Language Technology (Computational Linguistics)
Research subject
Computer and Information Sciences Computer Science
Identifiers
urn:nbn:se:vxu:diva-1206 (URN)
Presentation
2007-01-19, D1136, D-byggnaden, Växjö Universitet, Växjö, 13:15 (English)
Opponent
Supervisors
Available from: 2007-03-21 Created: 2007-03-21 Last updated: 2018-01-13Bibliographically approved
Organisations

Search in DiVA

Show all publications