Diff for "PDB/PDBparser"

Differences between revisions 1 and 84 (spanning 83 versions)

PDB-trained dependency parsing models for Polish

The PDB-based models are trained on the current version of Polish Dependency Bank with the publicly available parsing systems – COMBO-pytorch, COMBO, MateParser and MaltParser.

COMBO-pytorch model for dependency parsing only,
COMBO model for dependency parsing only
COMBO model for part-of-speech tagging, lemmatisation, and dependency parsing
COMBO model for part-of-speech tagging, lemmatisation, dependency parsing, and semantic role labelling

MATE model for dependency parsing
MaltParser model for dependency parsing

PDB-UD-trained dependency parsing models for Polish

The PDB-UD-based models are trained on the current version of Polish Dependency Bank in Universal Dependencies format with the publicly available parsing systems – COMBO-pytorch, COMBO, UDPipe.

COMBO-pytorch model for for part-of-speech tagging, lemmatisation, and dependency parsing (with HerBERT-base embeddings),
COMBO model for part-of-speech tagging, lemmatisation, and dependency parsing
COMBO model for part-of-speech tagging, lemmatisation, dependency parsing, and semantic role labelling
UDPipe model for tokenisation, part-of-speech tagging, lemmatisation, and dependency parsing
UDPipe model for tokenisation

Parsing performance

See Dependency parsing section.

190115_COMBO_PDB_nosem.pkl – PDB-based COMBO model for part-of-speech tagging, lemmatisation, and dependency parsing
190115_COMBO_PDB_sem.pkl – PDB-based COMBO model for part-of-speech tagging, lemmatisation, dependency parsing and semantic role labelling

NEW! PDB-based COMBO model compatible with the tagset of Morfeusz 2: 180912_PDBCOMBO.pkl
MateParser
- NEW! PDB-based Mate model compatible with the tagset of Morfeusz 2: 180322_PDBMate.mdl
- PDB-based Mate model compatible with the tagset of Morfeusz: 170608_PDBMate.mdl
MateParser
- 190125_MATE_PDB.model – PDB-based MateParser model for dependency parsing
MaltParser
- 190125_MALT_PDB.mco – PDB-based MaltParser model for dependency parsing
- NEW! PDB-based MaltParser model compatible with the tagset of Morfeusz 2: 180322_PDBMalt.mco
- PDB-basd MaltParser model compatible with the tagset of Morfeusz: 170608_PDBMalt.mco

10-fold cross-validation (avg.)

Model	LAS	UAS
`PDBMate`	0.85	0.89
`PDBMalt`	0.82	0.86

Precision, recall and f-score of individual dependency relations (avg.)

The description of Polish dependency relations types is available on Polish dependency relation types.

Dependency relation type	Precision		Recall		F-Measure
Dependency relation type	Mate	Malt	Mate	Malt	Mate	Malt
abbrev_punct	0.99	0.99	0.98	0.97	0.98	0.98
adjunct	0.89	0.73	0.92	0.77	0.82	0.75
adjunct_qt	0.74	0.51	0.76	0.58	0.75	0.55
aglt	1.00	0.98	1.00	0.98	0.98	0.98
app	0.75	0.58	0.69	0.52	0.72	0.55
aux	0.95	0.90	0.97	0.92	0.96	0.91
comp	0.90	0.85	0.87	0.82	0.88	0.84
comp_ag	0.95	0.90	0.96	0.91	0.94	0.90
comp_fin	0.87	0.75	0.86	0.79	0.87	0.77
comp_inf	0.95	0.91	0.96	0.90	0.93	0.90
cond	1.00	0.97	1.00	0.96	1.00	0.96
conjunct	0.85	0.71	0.82	0.65	0.82	0.68
imp	0.98	0.97	0.91	0.87	0.94	0.92
item	0.87	0.4	0.73	0.37	0.61	0.39
mwe	0.90	0.83	0.83	0.75	0.87	0.79
ne	0.87	0.78	0.73	0.64	0.76	0.70
neg	0.99	0.97	1.00	0.98	0.99	0.98
obj	0.89	0.81	0.91	0.86	0.89	0.83
obj_th	0.83	0.76	0.76	0.65	0.80	0.70
pd	0.86	0.77	0.80	0.72	0.87	0.74
pre_coord	0.86	0.76	0.78	0.55	0.82	0.64
punct	0.97	0.75	0.98	0.76	0.88	0.76
refl	0.99	0.96	0.99	0.96	0.99	0.96
root	0.91	0.80	0.91	0.81	0.94	0.80
subj	0.94	0.84	0.94	0.83	0.94	0.84

PDB-based dependency parsing demos

COMBO demo (only in Polish)
MaltParser demo in Multiservice NLP
- To parse a Polish text in Multiservice "Select predefined chain of actions": 5: Concraft, DependencyParser, input your text, and press the button "Run".
- To download the parser's output in CoNLL format, "Select output format:".

Publications

List of publications

Alina Wróblewska and Piotr Rybak. Dependency parsing of Polish. Poznań Studies in Contemporary Linguistics, 55(2):305–337, 2019.

(Note: Please contact the first author to get a copy of this article.) List of publications

Alina Wróblewska. Polish Dependency Parser Trained on an Automatically Induced Dependency Bank. Ph.D. dissertation, Institute of Computer Science, Polish Academy of Sciences, Warsaw, 2014.

List of publications

Alina Wróblewska and Adam Przepiórkowski. Projection-based annotation of a Polish dependency treebank. In Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis, editors, Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014, pages 2306–2312, Reykjavík, Iceland, 2014. European Language Resources Association (ELRA).

List of publications

Alina Wróblewska. Polish dependency bank. Linguistic Issues in Language Technology, 7(1), 2012.

List of publications

Alina Wróblewska and Marcin Woliński. Preliminary experiments in Polish dependency parsing. In Pascal Bouvry, Mieczysław A. Kłopotek, Franck Leprevost, Małgorzata Marciniak, Agnieszka Mykowiecka, and Henryk Rybiński, editors, Security and Intelligent Information Systems: International Joint Conference, SIIS 2011, Warsaw, Poland, June 13-14, 2011, Revised Selected Papers, number 7053 in Lecture Notes in Computer Science, pages 279–292. Springer-Verlag, 2012.

Licensing

The dependency parsing models for Polish are released under the CC BY-NC-SA 4.0 licence and by downloading them you accept the conditions of that licence.

Acknowledgment

The research was founded by SONATA 8 grant no 2014/15/D/HS2/03486 from the National Science Centre Poland and by the Polish Ministry of Science and Higher Education as part of the investment in the CLARIN-PL research infrastructure. The computing was performed at Poznań Supercomputing and Networking Center.

Contact

Any questions, comments? Please send them to <alina AT SPAMFREE ipipan DOT waw DOT pl>.

-  ⇤ ← Revision 1 as of 2017-06-12 20:33:30 → 
  Size: 14
  Editor: AlinaWroblewska
  Comment:
+   ← Revision 84 as of 2021-02-08 14:54:42 → ⇥
  Size: 11066
  Editor: AlinaWroblewska
  Comment:
-Deletions are marked like this.
+Additions are marked like this.
 Line 1:
-= PDBparser=
+#acl AlinaWroblewska:read,write,revert All:read
== PDB-trained dependency parsing models for Polish ==

The PDB-based models are trained on the current version of [[http://zil.ipipan.waw.pl/PDB|Polish Dependency Bank]] with the publicly available parsing systems – [[https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/tree/master|COMBO-pytorch]], [[https://github.com/360er0/COMBO|COMBO]], [[https://code.google.com/archive/p/mate-tools/|MateParser]] and [[http://maltparser.org|MaltParser]]. /* ''MaltParser'' is a transition-based dependency parser that uses a deterministic parsing algorithm. The deterministic parsing algorithm builds a dependency structure of an input sentence based on transitions (shift-reduce actions) predicted by a classifier. The classifier learns to predict the next transition given training data and the parse history. `MateParser`, in turn, is a graph-based parser that defines a space of well-formed candidate dependency trees for an input sentence, scores them given an induced parsing model, and selects the highest scoring dependency tree as a correct analysis of the input sentence. */

 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO_pytorch/model.tar.gz|COMBO-pytorch model]] for dependency parsing only,
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/20200930_COMBO_PDB_nosem_parseonly.pkl|COMBO model]] for dependency parsing only
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/200118_COMBO_PDB_nosem_full.pkl|COMBO model]] for part-of-speech tagging, lemmatisation, and dependency parsing
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/20200930_COMBO_PDBUD_sem.pkl|COMBO model]] for part-of-speech tagging, lemmatisation, dependency parsing, and semantic role labelling
{{{#!wiki comment
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/191107_COMBO_PDB_semlab_parseonly.pkl|COMBO model]] for (semantic) dependency parsing only}}}

 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/MATE/20190612_MATE_PDB.pkl|MATE model]] for dependency parsing
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/MALT/190125_MALT_PDB.mco|MaltParser model]] for dependency parsing


== PDB-UD-trained dependency parsing models for Polish ==
The PDB-UD-based models are trained on the current version of [[http://git.nlp.ipipan.waw.pl/alina/PDBUD|Polish Dependency Bank in Universal Dependencies format]] with the publicly available parsing systems – [[https://gitlab.clarin-pl.eu/syntactic-tools/combo/-/tree/master|COMBO-pytorch]], [[https://github.com/360er0/COMBO|COMBO]], [[http://ufal.mff.cuni.cz/udpipe|UDPipe]].

 * [[http://mozart.ipipan.waw.pl/~mklimaszewski/models/polish-herbert-base.tar.gz|COMBO-pytorch model]] for for part-of-speech tagging, lemmatisation, and dependency parsing (with [[https://huggingface.co/allegro/herbert-base-cased|HerBERT-base]] embeddings),
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/200118_COMBO_PDBUD_nosem_full.pkl|COMBO model]] for part-of-speech tagging, lemmatisation, and dependency parsing
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/COMBO/200118_COMBO_PDBUD_sem_full.pkl|COMBO model]] for part-of-speech tagging, lemmatisation, dependency parsing, and semantic role labelling
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/UDPIPE/20200930_PDBUD_ttp_embedd.udpipe|UDPipe model]] for tokenisation, part-of-speech tagging, lemmatisation, and dependency parsing
 * [[http://mozart.ipipan.waw.pl/~alina/Polish_dependency_parsing_models/UDPIPE/20200930_PDBUD_tokeniser.udpipe|UDPipe model]] for tokenisation

{{{#!wiki comment 
 * [[http://mozart.ipipan.waw.pl/~prybak/model_poleval2018/model_A_semi.pkl|COMBO]] model for Polish (the model estimated for the [[http://poleval.pl/tasks#task1|PolEval 2018]] competition)
 * [[attachment:180606_PDBUDPipe.udpipe|UDPipe]] model for Polish}}}

== Parsing performance ==

See [[http://clip.ipipan.waw.pl/benchmarks|Dependency parsing]] section.

{{{#!wiki comment
  * [[attachment:190115_COMBO_PDB_nosem.pkl]] – PDB-based COMBO model for part-of-speech tagging, lemmatisation, and dependency parsing
  * [[attachment: 190115_COMBO_PDB_sem.pkl]] – PDB-based COMBO model for part-of-speech tagging, lemmatisation, dependency parsing and semantic role labelling

 * '''NEW!''' PDB-based COMBO model compatible with the tagset of Morfeusz 2: [[attachment:180912_PDBCOMBO.pkl]]

 * MateParser

  * '''NEW!''' PDB-based Mate model compatible with the tagset of Morfeusz 2: [[attachment:180322_PDBMate.mdl]]
  * PDB-based Mate model compatible with the tagset of Morfeusz: [[attachment:170608_PDBMate.mdl]]

 * MateParser 
  * [[attachment:190125_MATE_PDB.model]] – PDB-based MateParser model for dependency parsing
 * MaltParser
  * [[attachment:190125_MALT_PDB.mco]] – PDB-based MaltParser model for dependency parsing


  * '''NEW!''' PDB-based MaltParser model compatible with the tagset of Morfeusz 2: [[attachment:180322_PDBMalt.mco]]
  * PDB-basd MaltParser model compatible with the tagset of Morfeusz: [[attachment:170608_PDBMalt.mco]]

=== 10-fold cross-validation (avg.) ===

|| '''Model''' || '''LAS''' || '''UAS''' ||
|| `PDBMate` || 0.85 || 0.89 ||
|| `PDBMalt` || 0.82 || 0.86 ||

=== Precision, recall and f-score of individual dependency relations (avg.) ===

The description of Polish dependency relations types is available on [[http://zil.ipipan.waw.pl/PDB/DepRelTypes|Polish dependency relation types]].

||<rowspan=2> '''Dependency relation type'''      |||| '''Precision''' |||| '''Recall'''  |||| '''F-Measure'''  ||
|| Mate || Malt   || Mate || Malt    || Mate || Malt ||
||<bgcolor="#eef3ff">abbrev_punct    ||<bgcolor="#eef3ff">0.99 ||<bgcolor="#eef3ff">0.99   ||<bgcolor="#eef3ff">0.98 ||<bgcolor="#eef3ff">0.97    ||<bgcolor="#eef3ff"> 0.98 ||<bgcolor="#eef3ff">0.98 ||
||adjunct         || 0.89 || 0.73   || 0.92 || 0.77    || 0.82 || 0.75 ||
||<bgcolor="#eef3ff">adjunct_qt      ||<bgcolor="#eef3ff"> 0.74 ||<bgcolor="#eef3ff"> 0.51   ||<bgcolor="#eef3ff"> 0.76 ||<bgcolor="#eef3ff"> 0.58    ||<bgcolor="#eef3ff"> 0.75 ||<bgcolor="#eef3ff"> 0.55 ||
||aglt            || 1.00 || 0.98   || 1.00 || 0.98    || 0.98 || 0.98 ||
||<bgcolor="#eef3ff">app             ||<bgcolor="#eef3ff"> 0.75 ||<bgcolor="#eef3ff"> 0.58   ||<bgcolor="#eef3ff"> 0.69 ||<bgcolor="#eef3ff"> 0.52    ||<bgcolor="#eef3ff"> 0.72 ||<bgcolor="#eef3ff"> 0.55 ||
||aux             || 0.95 || 0.90   || 0.97 || 0.92    || 0.96 || 0.91 ||
||<bgcolor="#eef3ff">comp            ||<bgcolor="#eef3ff"> 0.90 ||<bgcolor="#eef3ff"> 0.85   ||<bgcolor="#eef3ff"> 0.87 ||<bgcolor="#eef3ff"> 0.82    ||<bgcolor="#eef3ff"> 0.88 ||<bgcolor="#eef3ff"> 0.84 ||
||comp_ag         || 0.95 || 0.90   || 0.96 || 0.91    || 0.94 || 0.90 ||
||<bgcolor="#eef3ff">comp_fin        ||<bgcolor="#eef3ff"> 0.87 ||<bgcolor="#eef3ff"> 0.75   ||<bgcolor="#eef3ff"> 0.86 ||<bgcolor="#eef3ff"> 0.79    ||<bgcolor="#eef3ff"> 0.87 ||<bgcolor="#eef3ff"> 0.77 ||
||comp_inf        || 0.95 || 0.91   || 0.96 || 0.90    || 0.93 || 0.90 ||
||<bgcolor="#eef3ff">   cond     ||<bgcolor="#eef3ff"> 1.00 ||<bgcolor="#eef3ff"> 0.97	    ||<bgcolor="#eef3ff"> 1.00 ||<bgcolor="#eef3ff"> 	0.96       ||<bgcolor="#eef3ff"> 1.00 ||<bgcolor="#eef3ff"> 0.96    ||
||conjunct        || 0.85 || 0.71	    || 0.82 || 0.65	       || 0.82 || 0.68     ||
||<bgcolor="#eef3ff"> imp ||<bgcolor="#eef3ff">0.98 ||<bgcolor="#eef3ff">	0.97    ||<bgcolor="#eef3ff"> 0.91 ||<bgcolor="#eef3ff"> 	0.87       ||<bgcolor="#eef3ff">0.94 ||<bgcolor="#eef3ff">  0.92   ||
|| item            || 0.87 ||  0.4	    ||  0.73 ||  0.37	       || 0.61 || 0.39     ||
||<bgcolor="#eef3ff">    mwe    ||<bgcolor="#eef3ff"> 0.90 ||<bgcolor="#eef3ff">	0.83    ||<bgcolor="#eef3ff"> 0.83 ||<bgcolor="#eef3ff"> 0.75	       ||<bgcolor="#eef3ff">0.87 ||<bgcolor="#eef3ff">  0.79   ||
||ne              ||  0.87 || 0.78	    || 0.73 || 0.64	       ||  0.76 ||  0.70     ||
||<bgcolor="#eef3ff">   neg     ||<bgcolor="#eef3ff">0.99 ||<bgcolor="#eef3ff">	 0.97   ||<bgcolor="#eef3ff"> 1.00 ||<bgcolor="#eef3ff"> 0.98	       ||<bgcolor="#eef3ff">0.99  ||<bgcolor="#eef3ff">  0.98   ||
||obj             || 0.89 || 0.81	    || 0.91 || 0.86	       ||  0.89 || 0.83     ||
||<bgcolor="#eef3ff">     obj_th   ||<bgcolor="#eef3ff">0.83 ||<bgcolor="#eef3ff">	0.76    ||<bgcolor="#eef3ff"> 0.76  ||<bgcolor="#eef3ff"> 	0.65       ||<bgcolor="#eef3ff">0.80 ||<bgcolor="#eef3ff">  0.70   ||
||pd              || 0.86 || 0.77	    || 0.80 || 0.72	       || 0.87 || 0.74      ||
||<bgcolor="#eef3ff">  pre_coord      ||<bgcolor="#eef3ff">0.86 ||<bgcolor="#eef3ff">	0.76    ||<bgcolor="#eef3ff">0.78 ||<bgcolor="#eef3ff"> 0.55	       ||<bgcolor="#eef3ff">0.82 ||<bgcolor="#eef3ff">   0.64  ||
||punct           || 0.97 || 0.75	    || 0.98 || 0.76	       || 0.88 || 0.76     ||
||<bgcolor="#eef3ff">refl            ||<bgcolor="#eef3ff"> 0.99 ||<bgcolor="#eef3ff"> 0.96	    ||<bgcolor="#eef3ff"> 0.99 ||<bgcolor="#eef3ff"> 0.96	       ||<bgcolor="#eef3ff"> 0.99 ||<bgcolor="#eef3ff"> 0.96     ||
||root            || 0.91 || 0.80	    || 0.91 || 0.81	       || 0.94 ||0.80     ||
||<bgcolor="#eef3ff">    subj    ||<bgcolor="#eef3ff"> 0.94||<bgcolor="#eef3ff">	   0.84 ||<bgcolor="#eef3ff">0.94 ||<bgcolor="#eef3ff"> 	0.83       ||<bgcolor="#eef3ff">0.94 ||<bgcolor="#eef3ff"> 0.84    ||
}}}

== PDB-based dependency parsing demos ==

 * [[http://scwad-demo.nlp.ipipan.waw.pl:8000/dependency-parsing|COMBO demo]] (only in Polish)
 * [[http://multiservice.nlp.ipipan.waw.pl|MaltParser demo in Multiservice NLP]]
  * To parse a Polish text in Multiservice "Select predefined chain of actions": 5: Concraft, !DependencyParser, input your text, and press the button "Run".
  * To download the parser's output in CoNLL format, "Select output format:".

== Publications ==

<<BibMate(key, "wro:ryb:2019", omitYears=true)>> (Note: Please contact the first author to get a copy of this article.)
<<BibMate(key, "wro:14", omitYears=true)>>
<<BibMate(key, "wro:prz:14", omitYears=true)>>
<<BibMate(key, "wroblewska:12", omitYears=true)>>
<<BibMate(key, "awmw:deparsing", omitYears=true)>>


== Licensing ==

The dependency parsing models for Polish are released under the [[https://creativecommons.org/licenses/by-nc-sa/4.0/|CC BY-NC-SA 4.0]] licence and by downloading them you accept the conditions of that licence.

== Acknowledgment ==
The research was founded by SONATA 8 grant no 2014/15/D/HS2/03486 from the National Science Centre Poland and by the Polish Ministry of Science and Higher Education as part of the investment in the CLARIN-PL research infrastructure. The computing was performed at Poznań Supercomputing and Networking Center.


== Contact ==
Any questions, comments? Please send them to <<MailTo(alina AT SPAMFREE ipipan DOT waw DOT pl)>>.

Diff for "PDB/PDBparser"

Menu

PDB-trained dependency parsing models for Polish

PDB-UD-trained dependency parsing models for Polish

Parsing performance

10-fold cross-validation (avg.)

Precision, recall and f-score of individual dependency relations (avg.)

PDB-based dependency parsing demos

Publications

Licensing

Acknowledgment

Contact