AplikaceAplikace
Nastavení

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
en:pojmy:syntakticka_analyza [2022/08/13 13:08] – [Syntactic analysis and syntactic tagging] alexandrrosenen:pojmy:syntakticka_analyza [2026/01/19 10:45] (current) – [Visualisation of syntactic structures in KonText] tomasjelinek
Line 9: Line 9:
 ==== Automatic syntactic annotation: parsing ==== ==== Automatic syntactic annotation: parsing ====
  
-Syntactic annotation is done automatically, using a syntactic ([[en:pojmy:parser|parser]]). For the annotation of the SYN2015 corpus, the TurboParser was used, for SYN2020, a "neural" parser of the NeuroNLP2 tools was used. This kind of annotation has a higher error rate than [[en:pojmy:morfologicka_analyza|morphological annotation]]. In SYN2020, more than 1/9 [[en:pojmy:token|tokens]] are left without a correctly identified „parent“ or correctly matched syntactic function, in SYN2015, it's as much as 1/6 of [[en:pojmy:token|tokens]].\\+Syntactic annotation is done automatically, using a syntactic ([[en:pojmy:parser|parser]]). For the annotation of the SYN2015 corpus, the TurboParser was used, for SYN2020 and SYN2025, a neural parser of the NeuroNLP2 tools was used. This kind of annotation has a higher error rate than [[en:pojmy:morfologicka_analyza|morphological annotation]]. In SYN2020, more than 1/9 [[en:pojmy:token|tokens]] are left without a correctly identified „parent“ or correctly matched syntactic function, in SYN2015, it's as much as 1/6 of [[en:pojmy:token|tokens]].\\
 The success rate of parsing is measured as UAS (unlabeled attachment score), the rate of successful parent identification, and LAS (labeled attachment score), the rate of successful identification of both parent and syntactic function. In the SYN2015 and SYN2020, these rates are as follows: The success rate of parsing is measured as UAS (unlabeled attachment score), the rate of successful parent identification, and LAS (labeled attachment score), the rate of successful identification of both parent and syntactic function. In the SYN2015 and SYN2020, these rates are as follows:
  
Line 15: Line 15:
 | SYN2015 | 88,48 % | 82,46 % | | SYN2015 | 88,48 % | 82,46 % |
 | SYN2020 | 92,39 % | 88,73 % | | SYN2020 | 92,39 % | 88,73 % |
 +| SYN2025 | 92,56 % | 88,94 % |
  
  
Line 32: Line 33:
 ===== Visualisation of syntactic structures in KonText ===== ===== Visualisation of syntactic structures in KonText =====
  
-For every sentence in a syntactically annotated corpus (currently [[en:cnk:syn2015|SYN2015]] and [[en:cnk:syn2020|SYN2020]]), a syntactic structure can be visualised by clicking on a little icon representing a syntactic tree on the left side of a concordance line (marked with a red circle in the following image):\\+For every sentence in a syntactically annotated corpus (currently [[en:cnk:syn2025|SYN2025]], [[en:cnk:syn2025|SYN2025]]) and [[en:cnk:syn2015|SYN2015]]), a syntactic structure can be visualised by clicking on a little icon representing a syntactic tree on the left side of a concordance line (marked with a red circle in the following image):\\
  
 {{:pojmy:zobrazenisyntaxe.png?500|Syntactic structure visualisation}}\\ {{:pojmy:zobrazenisyntaxe.png?500|Syntactic structure visualisation}}\\

Trace: