Changes between Initial Version and Version 1 of en/AdvancedNlpCourse2018/ParsingCzech


Ignore:
Timestamp:
Sep 12, 2019, 11:11:35 AM (14 months ago)
Author:
Ales Horak
Comment:

copied from private/AdvancedNlpCourse/ParsingCzech

Legend:

Unmodified
Added
Removed
Modified
  • en/AdvancedNlpCourse2018/ParsingCzech

    v1 v1  
     1= Parsing of Czech: Between Rules and Stats =
     2
     3[[https://is.muni.cz/auth/predmet/fi/ia161|IA161]] [[en/AdvancedNlpCourse|Advanced NLP Course]], Course Guarantee: Aleš Horák
     4
     5Prepared by: Miloš Jakubíček
     6
     7== State of the Art ==
     8
     9=== References ===
     10
     11 1. PEI, Wenzhe; GE, Tao; CHANG, Baobao. An effective neural network model for graph-based dependency parsing. In: Proc. of ACL. 2015.
     12 1. CHOI, Jinho D.; TETREAULT, Joel; STENT, Amanda. It Depends: Dependency Parser Comparison Using A Web-based Evaluation Tool. In: Proc. of ACL. 2015.
     13 1. DURRETT, Greg; KLEIN, Dan. Neural CRF Parsing. In: Proc. of ACL. 2015.
     14
     15== Practical Session ==
     16
     17 1. Go to http://ske.fi.muni.cz, login and create a shadow copy of the Czech Wikipedia corpus by clicking on [[Image(add.png,valign=middle,nolink,class=intext)]]''Create grammar development corpus'' (if you do not have such link at the bottom of the main page, ask for it).
     18 1. Develop your own sketch grammar that will capture the following semantic relations in this corpus: hypernymy/hyponymy, meronymy/holonymy (hint: use {{{DUAL}}} directive), optionally you can develop more relations (e.g. "is-defined-as").
     19    Read related [https://www.sketchengine.co.uk/writing-sketch-grammars/ documentation]. Start with a couple of simple CQL queries that you pretest in the interface.
     20 1. You can iteratively expand the grammar, upload it into the system, have the system compute word sketches and review the results
     21 1. When you are happy with the grammar, process the raw !WordSketch data (output of `dumpws` command) of your corpus. The data can be obtained in two ways:
     22  1. smaller data (up to 100,000 relations) can be downloaded from web: [[BR]]
     23   `https://ske.fi.muni.cz/bonito/r.cgi/dumpws?corpname=user/<YOUR_USERNAME_IN_SKETCH_ENGINE>/gramdev_czechwiki` [[BR]]
     24   e.g. [[BR]]
     25   https://ske.fi.muni.cz/bonito/r.cgi/dumpws?corpname=user/novakjan/gramdev_czechwiki [[BR]]
     26   [[BR]]
     27   First, you have to be authenticated at https://ske.fi.muni.cz/login/.
     28   `gramdev_czechwiki` is the ''corpus_id'' of the Czech Wikipedia corpus. [[BR]]
     29   Or, if you need more than 100,000 relations, you can use the other way
     30  1. logon to the {{{alba.fi.muni.cz}}} server and use the {{{dumpws}}} command to export the content of the word sketch database: [[BR]]
     31   {{{dumpws /corpora/ca/user_data/<YOUR_USERNAME_IN_SKETCH_ENGINE>/registry/gramdev_czechwiki}}} [[BR]]
     32   For this you may need to ask for extra permission to registry directories.
     33 5. Process the output of {{{dumpws}}} with a simple Bash or Python script to select first 100 most salient headword-collocation pairs for each relation. Upload the resulting list into the IS vault.