Difference between revisions of "User:Eortici1/Final project"

From LING073
Jump to: navigation, search
(→‎Evaluation)
Line 1: Line 1:
 
This page documents my final project, a larger UD corpus and annotation guidelines for Bikol.
 
This page documents my final project, a larger UD corpus and annotation guidelines for Bikol.
−
 
−
* [http://universaldependencies.org/new_language.html UD Procedures for new languages]
 
  
 
Issues
 
Issues
 
* links
 
* links
 
* mga
 
* mga
−
 
−
Change sarong to a determiner instead of an nmod?
 
−
 
−
Check notes on phone for some changes to be made.
 
  
 
Re-evaluate NA !!!
 
Re-evaluate NA !!!
Line 15: Line 9:
 
* check @dep and anything labeled !*  
 
* check @dep and anything labeled !*  
  
−
tr -cd @ < bcl.annotated.large.ud.txt | wc -c
 
−
* counts number of @ in the file
 
  
 
== Corpus Information ==
 
== Corpus Information ==
Line 29: Line 21:
 
|1163
 
|1163
 
|}
 
|}
 +
  
 
This corpus contains extracts from the following sources:
 
This corpus contains extracts from the following sources:
 
* [http://www.ohchr.org/EN/UDHR/Pages/Language.aspx?LangID=bkl Universal Declaration of Human Rights] (used [http://www.ohchr.org/EN/UDHR/Pages/Language.aspx?LangID=eng English translation] for glosses)
 
* [http://www.ohchr.org/EN/UDHR/Pages/Language.aspx?LangID=bkl Universal Declaration of Human Rights] (used [http://www.ohchr.org/EN/UDHR/Pages/Language.aspx?LangID=eng English translation] for glosses)
−
* [http://bcl.wikipedia.org Various Bikol Wikipedia articles], accessed from 01/05/2017 to 10/05/2017
+
* [http://bcl.wikipedia.org Various Bikol Wikipedia articles], accessed from 01/05/2017 to 08/05/2017
  
 
== Evaluation ==
 
== Evaluation ==
 +
 +
Parsers are typically evaluated with the LAS (Label Attachment Score) and UAS (Unlabeled Attachment Score) obtained by testing on a separate corpus. However, making an additional, separate corpus would be time consuming. To get around this, I divided the corpus into 10 roughly equal parts (10-11 sentences each). Then, I used each part as a test corpus for two parsers (with and without morphological information) which were trained on the remaining corpus.
 +
 +
The partial corpora, conllu and udpipe files can all be found in the [https://github.swarthmore.edu/eortici1/UD_Bikol/tree/master/bcl-eval bcl-eval directory] of the repository. The data from all the individual tests can be found in the Appendix of this Wiki page.
 +
 +
To evaluate the [https://github.swarthmore.edu/eortici1/UD_Bikol/tree/master/dev parsers trained on the entire corpus], I took the average of all the UAS/LAS scores obtained on the 10 test sets, ± the standard deviation. The results are displayed below.
  
 
{| class="wikitable"
 
{| class="wikitable"

Revision as of 04:00, 10 May 2017

This page documents my final project, a larger UD corpus and annotation guidelines for Bikol.

Issues

  • links
  • mga

Re-evaluate NA !!!

  • aux:amod, aux:nmod, aux:advmod, aux:nummod
  • check @dep and anything labeled !*


Corpus Information

Corpus Size
Sentences Forms
103 1163


This corpus contains extracts from the following sources:

Evaluation

Parsers are typically evaluated with the LAS (Label Attachment Score) and UAS (Unlabeled Attachment Score) obtained by testing on a separate corpus. However, making an additional, separate corpus would be time consuming. To get around this, I divided the corpus into 10 roughly equal parts (10-11 sentences each). Then, I used each part as a test corpus for two parsers (with and without morphological information) which were trained on the remaining corpus.

The partial corpora, conllu and udpipe files can all be found in the bcl-eval directory of the repository. The data from all the individual tests can be found in the Appendix of this Wiki page.

To evaluate the parsers trained on the entire corpus, I took the average of all the UAS/LAS scores obtained on the 10 test sets, ± the standard deviation. The results are displayed below.

Evaluation of bcl-withmorph.udpipe
UAS LAS
60.87 ± 5.67 50.00 ± 4.22
Evaluation of bcl-nomorph.udpipe
UAS LAS
50.51 ± 5.53 36.01 ± 6.59

UD Annotation Guidelines

Appendix

Evaluation

UD Parser Evaluation: Tests on 10 Subsets of Corpus
UAS with morphology LAS with morphology UAS without morphology LAS without morphology
Test 1 55.37 45.45 48.76 31.40
Test 2 56.34 46.48 50.70 38.03
Test 3 64.29 54.46 57.14 43.75
Test 4 65.00 49.17 53.33 36.67
Test 5 56.44 47.52 40.59 23.76
Test 6 65.52 52.41 56.55 38.62
Test 7 52.89 44.63 46.28 31.40
Test 8 57.45 48.94 45.74 34.04
Test 9 67.65 53.92 49.02 35.29
Test 10 67.77 57.02 57.02 47.11