Difference between revisions of "Shallow syntactic function labeller"
Jump to navigation
Jump to search
Deltamachine (talk | contribs) |
Deltamachine (talk | contribs) |
||
| Line 1: | Line 1: | ||
This is [http://wiki.apertium.org/wiki/User:Deltamachine/proposal Google Summer of Code 2017 project] |
This is [http://wiki.apertium.org/wiki/User:Deltamachine/proposal Google Summer of Code 2017 project] |
||
| − | A repository for the project: https://github.com/deltamachine/shallow_syntactic_function_labeller |
+ | A repository for the whole project: https://github.com/deltamachine/shallow_syntactic_function_labeller |
| + | A workplan and progress notes can be found here: [[Shallow syntactic function labeller/Workplan]] |
||
| − | == Architecture == |
||
| + | == Testing == |
||
| − | <p>1. The labeller takes a string in Apertium stream format with morphological tags:</p> |
||
| + | == To do == |
||
| − | <blockquote> |
||
| + | '''* Add an ability to handle more than one sentence.''' |
||
| − | ^vino<n><m><sg>$ = INPUT |
||
| + | * Do more tests. MORE. |
||
| − | </blockquote> |
||
| + | * Write docstrings and refactore the main code. |
||
| − | |||
| + | * Take the trash out of the github repository before the final evaluation. |
||
| − | <p>2. Parses it into a sequence of morphological tags:</p> |
||
| + | * Continue improving the perfomance of the models. |
||
| − | |||
| − | <blockquote><n><m><sg> |
||
| − | </blockquote> |
||
| − | |||
| − | <p>3. Restores the model for this language (which is in the same directory and looks like .json file or like a .pkl file)</p> |
||
| − | |||
| − | <p>4. The algorithm analyzes the string and gives a sequence of syntactic tags as an output.</p> |
||
| − | <blockquote> |
||
| − | <@nsubj> |
||
| − | </blockquote> |
||
| − | <p>5. The labeller applies given labels to the original string:</p> |
||
| − | <blockquote>^vino<n><m><sg><@nsubj>$ = OUTPUT |
||
| − | </blockquote> |
||
| − | <p></p> |
||
| − | <p> So, in the end there will be a module itself and a file with a model. </p> |
||
| − | |||
| − | == Workplan == |
||
| − | |||
| − | {|class=wikitable |
||
| − | |- |
||
| − | ! Week !! Dates !! To do |
||
| − | |- |
||
| − | | 1 || 30th May — 5th June || |
||
| − | * <s>Handling discrepancies between Apertium sme-nob and Sami corpus tagsets</s> |
||
| − | * <s>Writing a script for parsing Sami corpus</s> |
||
| − | |- |
||
| − | | 2 |
||
| − | | 6th June — 12th June |
||
| − | | rowspan="2" align=left " | <s>Writing scripts for replacing UD tags with suitable Apertium tags and parsing UD-tree into a dataset for Kazakh, Breton and English UD dependency treebanks</s> |
||
| − | |||
| − | |- |
||
| − | | 3 |
||
| − | | 13th June — 19th June |
||
| − | |||
| − | |- |
||
| − | | 4 || 20th June — 26th June || <s>Writing scripts for converting UD-treebanks (dev and test) of needed languages in Apertium stream format (converted treebanks will be useful for evaluating the quality of the labeller</s>) |
||
| − | |||
| − | |- |
||
| − | ! '''First evaluation''' !! colspan="2" align=left | |
||
| − | Ready-to-use datasets |
||
| − | |- |
||
| − | | 5 |
||
| − | | 27th June — 3rd July |
||
| − | | rowspan="2" align=left " | <s>Building and training the classifier</s> |
||
| − | |- |
||
| − | | 6 |
||
| − | | 4th Jule — 10th July |
||
| − | |- |
||
| − | | 7 || 11th July — 17th July || |
||
| − | <s>* Further training |
||
| − | * Working on improvements of the model</s> |
||
| − | |- |
||
| − | | 8 || 18th July — 24th July || |
||
| − | <s>Working on improvements of the model</s> |
||
| − | |- |
||
| − | !'''Second evaluation''' || colspan="2" align=left | |
||
| − | Well-trained models |
||
| − | |- |
||
| − | | 9 || 25th July — 31th July || |
||
| − | * Collecting all parts of the labeller together |
||
| − | * Adding machine-learned module instead of the syntax labelling part of sme-nob CG module to test it |
||
| − | |- |
||
| − | | 10 || 1st August — 7th August || |
||
| − | * Adding machine-learned module instead of the syntax labelling part of sme-nob CG module to test it |
||
| − | |- |
||
| − | | 11 || 8th August — 14th August || |
||
| − | * Testing |
||
| − | * Fixing bugs |
||
| − | |- |
||
| − | | 12 || 15th August — 21th August || |
||
| − | * Cleaning up the code |
||
| − | * Writing documentation |
||
| − | |- |
||
| − | !'''Final evaluation''' || colspan="2" align=left | |
||
| − | The prototype shallow syntactic function labeller. |
||
| − | |- |
||
| − | |} |
||
| − | |||
| − | == Progress == |
||
| − | '''Week 1:''' Datasets for North Sami were created. |
||
| − | * Some tags in the original corpus were replaced with Apertium North Sami tags (like here: https://victorio.uit.no/langtech/trunk/langs/sme/tools/mt/apertium/tagsets/modify-tags.regex). |
||
| − | * Some tags were removed from the original corpus as irrelevant: ABBR, ACR, Allegro, G3, G7, <ext>, Foc_, Qst. |
||
| − | * In cases when there were two lines with analysis for one word, only one analysis has been left. |
||
| − | * Information about derivation was removed too. |
||
| − | * Special "fake" syntactical functions were added for CLB and PUNCT: @CLB and @PUNCT. |
||
| − | * Two types of datasets were created: the first type contains tags for punctuation and clause boundaries and the second does not. |
||
| − | |||
| − | '''Weeks 2-3:''' Datasets for Kazakh, Breton and English were created. |
||
| − | |||
| − | NB: the datasets for North Sami and English seem to be pretty big, when Kazakh is comparably small and Breton is even smaller. But it gives us opportunity to check how many data will be enough for training the labeller and is it possible to achieve pretty good results having very small amount of data (like in case of Breton) |
||
| − | * All dependency treebanks were "flattened": words with the @conj and the @parataxis relation took the label of their head (https://github.com/deltamachine/wannabe_hackerman/blob/master/flatten_conllu.py). |
||
| − | * For all languages two types of datasets were created: the first type contains tags for punctuation and the second does not. |
||
| − | * ''Kazakh'' |
||
| − | ** some mistakes in conllu file were corrected |
||
| − | ** double lines were removed |
||
| − | * ''English'' |
||
| − | ** double lines were removed |
||
| − | ** all UD POS and features tags were replaced with Apertium tags |
||
| − | * ''Breton'' |
||
| − | ** some mistakes in conllu file were corrected |
||
| − | ** double lines were removed |
||
| − | ** all UD features tags were replaced with Apertium tags |
||
| − | |||
| − | '''Week 4:''' Scripts for converting Kazakh, Breton and English UD-treebanks in Apertium stream format were written |
||
| − | |||
| − | '''Weeks 5-6:''' |
||
| − | Two types of networks were built: a simple RNN network and an encoder-decoder network with attentive mechanism. |
||
| − | It seems that simple RNN shows better results in all our cases. Encoder-decoder network shows acceptable results only |
||
| − | on very big datasets, like English dataset, but in case of small corpus, like Breton, it is useless, and simple RNN can work with small datasets. |
||
| − | |||
| − | '''Weeks 7-8:''' |
||
| − | What new was created: |
||
| − | * New datasets (tokens + tags instead of just tags) |
||
| − | * Word2vec and fastText embeddings |
||
| − | |||
| − | Fasttext embeddings helped to improve accuracy of Kazakh model on 10% and accuracy of English model on 3%. |
||
| − | Current results: 76% for Breton, 78% for Kazakh, 82% for North Sami and 80% for English. |
||
| − | However, models are still need to be improved somehow. |
||
Revision as of 17:02, 13 August 2017
This is Google Summer of Code 2017 project
A repository for the whole project: https://github.com/deltamachine/shallow_syntactic_function_labeller
A workplan and progress notes can be found here: Shallow syntactic function labeller/Workplan
Testing
To do
* Add an ability to handle more than one sentence.
- Do more tests. MORE.
- Write docstrings and refactore the main code.
- Take the trash out of the github repository before the final evaluation.
- Continue improving the perfomance of the models.
