Shallow syntactic function labeller - Revision history

Sushain at 01:40, 8 March 2018

2018-03-08T01:40:25Z

2017-08-31T14:20:25Z

Bugs

2017-08-31T14:19:38Z

Bugs

2017-08-28T13:44:05Z

What was done

2017-08-28T13:19:06Z

To do

2017-08-28T09:43:05Z

Bugs

2017-08-27T20:59:56Z

Bugs

2017-08-27T11:15:19Z

2017-08-27T08:41:53Z

2017-08-22T12:44:29Z

To do

@@ Line 70: / Line 70: @@
 . Python libraries:
 * DyNet (installation instructions can be found here: http://dynet.readthedocs.io/en/latest/python.html)
-* Streamparser (https://github.com/goavki/streamparser)
+* Streamparser (https://github.com/apertium/streamparser)
 . Precompiled language pairs which support the labeller (sme-nob, kmr-eng)

@@ Line 112: / Line 112: @@
 </pre>
-and 3 seem to be fixed, but it chould be checked carefully.
+and 3 seem to be fixed, but it should be checked carefully.
 == To do ==

@@ Line 99: / Line 99: @@
 == Bugs ==
-* <s>Installation script changes eng-kmr pipeline along with kmr-eng</s>
+. <s>Installation script changes eng-kmr pipeline along with kmr-eng</s>
-* <s>Problems with tags order (syntactic label is not the last tag)</s> - seems to be fixed, but it should be checked carefully.
+. <s>Problems with tags order (syntactic label is not the last tag)</s>
-* Words-without-a-label bug
+. <s>Words-without-a-label bug</s>
 <pre>
 <spectre> is it possible that some words don't get a label ?
@@ Line 109: / Line 111: @@
 ^kirin<vblex><tv><past><p3><sg>$^..<sent><@punct>$
 </pre>
+and 3 seem to be fixed, but it chould be checked carefully.
 == To do ==

@@ Line 10: / Line 10: @@
 . Simple RNN, which is able to label sentences, was built. It works with fastText embeddings for every tag which was seen in the corpus: an embedding for a word is just a sum of all word's tags embeddings.
-. The testpack for two language pairs was built: it contains all needed data for sme-nob and kmr-eng, the labeller itself and installation script.
+. The labeller itself was created. Also the testpack for two language pairs was built: it contains all needed data for sme-nob and kmr-eng, the labeller and installation script.
 == List of commits ==

@@ Line 112: / Line 112: @@
 == To do ==
 * Do more tests. MORE.
+* '''Fix bugs'''
 * Refactore the main code.
 * '''Continue improving the perfomance of the models.'''

@@ Line 96: / Line 96: @@
 <pre>
 python setup.py -cg -sme
+</pre>
+== Bugs ==
+* Installation script changes eng-kmr pipeline along with kmr-eng
+* Words-without-a-label bug
+<pre>
+<spectre> is it possible that some words don't get a label ?
+<spectre> $ echo "Barzanî di peyama xwe de behsa mijarên girîng û kirîtîk kir." | apertium -d . kmr-eng-tagger
+<spectre> ^Barzanî<np><ant><m><sg><obl><@dobj>$ ^di<pr><@case>$ ^peyam<n><f><sg><con><def><@nmod>$ ^xwe<prn><ref><mf><sp><@nmod:poss>$
+^de<post><@case>$ ^behs<n><f><sg><con><def>$ ^mijar<n><f><pl><con><def><@nmod:poss>$ ^girîng<adj><@amod>$ ^û<cnjcoo><@cc>$ ^*kirîtîk$
+^kirin<vblex><tv><past><p3><sg>$^..<sent><@punct>$
 </pre>

@@ Line 4: / Line 4: @@
 A workplan and progress notes can be found here: [[Shallow syntactic function labeller/Workplan]]
+== What was done ==
+. All needed data for North Sami, Kurmanji, Breton, Kazakh and English was prepared: there are two scripts, one of which creates datasets from UD treebanks (it is able to handle Kurmanji, Breton, Kazakh and English) and the second creates datasets from VISL treebanks (is able to handle North Sami).
+. Simple RNN, which is able to label sentences, was built. It works with fastText embeddings for every tag which was seen in the corpus: an embedding for a word is just a sum of all word's tags embeddings.
+. The testpack for two language pairs was built: it contains all needed data for sme-nob and kmr-eng, the labeller itself and installation script.
+== List of commits ==
+All commits are listed below:
+https://github.com/deltamachine/shallow_syntactic_function_labeller/commits/master
 == Description ==
@@ Line 87: / Line 99: @@
 == To do ==
-* <s>Add an ability to handle more than one sentence.</s>
-* <s>Write docstrings.</s>
-* <s>Take the trash out of the github repository before the final evaluation.</s>
 * Do more tests. MORE.
 * Refactore the main code.
-* Continue improving the perfomance of the models.
+* '''Continue improving the perfomance of the models.'''