Segmentation Charts for Czech – Relations among Segments in Complex Sentences

Lopatková, Markéta; Holan, Tomáš

doi:10.1007/978-3-642-00982-2_46

Cited by 3 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We examined two segmentation tools that aim at the identification of a level of embedding for individual segments and at the identification of individual clauses, respectively, using the a-layer of PDT: (1) the rule-based tool described in Lopatková and Holan (2009) (LH in Table 2; the tool provides levels of embedding for individual segments only, clauses are not identified), and (2) the tool based on machine learning methods described in Krůza and Kuboň (2009) (KK in Table 2; the algorithm specifies clauses directly, it does not work with the concept of segments). The numbers clearly confirm that the results of existing segmentation tools are not satisfactory yet.…”

Section: Results For the Existing Automatic Toolsmentioning

confidence: 99%

“…We exploit a concept of segments-linguistically motivated units, which may be easily detected automatically, as they were defined by Lopatková and Holan (2009). 1 The segment annotation captures relationships among segments, especially subordination, coordination, apposition and parenthesis.…”

Section: Motivationmentioning

confidence: 99%

“…Let us refer to the experiments described by Lopatková and Holan (2009) and by Krůza and Kuboň (2009). In both papers, the authors describe well-developed automatic procedures for identifying segments and/or clauses and their mutual relationship from the analytical layer of the PDT (i.e., a layer of surface syntax, see Hajič et al 2004), which is based on Czech grammatical tradition, see esp.…”

Section: Prague Dependency Treebank and Segment Annotationmentioning

confidence: 99%

“…However, the main purpose of identifying sentence structure-either manually or automatically from the PDT (using a reliable automatic tool)-is to gain development data for an automatic tool which would determine the overall structure of a (morphologically analyzed) sentence (the first results based on a small data sample are reported by Lopatková and Holan 2009).…”

Section: Prague Dependency Treebank and Segment Annotationmentioning

confidence: 99%

“…3 E.g., in experiments reported byLopatková and Holan (2009), a correct level of embedding was assigned only to approx. 75% of segments.Annotation of sentence structure 27…”

mentioning

confidence: 99%

See 4 more Smart Citations

Annotation of sentence structure

Lopatková

Homola

Klyueva

2011

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

The focus of this article is on the creation of a collection of sentences manually annotated with respect to their sentence structure. We show that the concept of linear segments-linguistically motivated units, which may be easily detected automatically-serves as a good basis for the identification of clauses in Czech. The segment annotation captures such relationships as subordination, coordination, apposition and parenthesis; based on segmentation charts, individual clauses forming a complex sentence are identified. The annotation of a sentence structure enriches a dependency-based framework with explicit syntactic information on relations among complex units like clauses. We have gathered a collection of 3,444 sentences from the Prague Dependency Treebank, which were annotated with respect to their sentence structure (these sentences comprise 10,746 segments forming 6,341 clauses). The main purpose of the project is to gain a development data-promising results for Czech NLP tools (as a dependency parser or a machine translation system for related languages) that adopt an idea of clause segmentation have been already reported. The collection of sentences with annotated sentence structure provides the possibility of further improvement of such tools.

show abstract

Section: Results For the Existing Automatic Toolsmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Prague Dependency Treebank and Segment Annotationmentioning

confidence: 99%

Section: Prague Dependency Treebank and Segment Annotationmentioning

confidence: 99%

“…3 E.g., in experiments reported byLopatková and Holan (2009), a correct level of embedding was assigned only to approx. 75% of segments.Annotation of sentence structure 27…”

mentioning

confidence: 99%

See 3 more Smart Citations

Annotation of sentence structure

Lopatková

Homola

Klyueva

2011

Lang Resources & Evaluation

Self Cite

View full text Add to dashboard Cite

show abstract

Improving Dependency Parsing Using Sentence Clause Charts

Kríž

Hladká

2016

Proceedings of the ACL 2016 Student Research Workshop

View full text Add to dashboard Cite

We propose a method for improving the dependency parsing of complex sentences. This method assumes segmentation of input sentences into clauses and does not require to retrain a parser of one's choice. We represent a sentence clause structure using clause charts that provide a layer of embedding for each clause in the sentence. Then we formulate a parsing strategy as a two-stage process where (i) coordinated and subordinated clauses of the sentence are parsed separately with respect to the sentence clause chart and (ii) their dependency trees become subtrees of the final tree of the sentence. The object language is Czech and the parser used is a maximum spanning tree parser trained on the Prague Dependency Treebank. We have achieved an average 0.97% improvement in the unlabeled attachment score. Although the method has been designed for the dependency parsing of Czech, it is useful for other parsing techniques and languages.

show abstract

Annotation of sentence structure

Lopatková

Klyueva

Homola

2009

Proceedings of the Third Linguistic Annotation Workshop on - ACL-IJCNLP '09

Self Cite

View full text Add to dashboard Cite

The goal of the presented project is to assign a structure of clauses to Czech sentences from the Prague Dependency Treebank (PDT) as a new layer of syntactic annotation, a layer of clause structure. The annotation is based on the concept of segments, linguistically motivated and easily automatically detectable units. The task of the annotators is to identify relations among segments, especially relations of super/subordination, coordination, apposition and parenthesis. Then they identify individual clauses forming complex sentences.In the pilot phase of the annotation, 2,699 sentences from PDT were annotated with respect to their sentence structure.

show abstract

Segmentation Charts for Czech – Relations among Segments in Complex Sentences

Cited by 3 publications

References 6 publications

Annotation of sentence structure

Annotation of sentence structure

Improving Dependency Parsing Using Sentence Clause Charts

Annotation of sentence structure

Contact Info

Product

Resources

About