github.com/cdli-gh/Semantic-Role-Labeler commits

Nlpnet word embedding feature loaded

335cb8322c10790ef206d8abd9f6ce53fb067179 authored over 6 years ago by Bakhtiyar <[email protected]>

Modifying script for saving embeddings in word2vec format

2bb4de2611bfe3aa9832f1f216a284967e95f363 authored over 6 years ago by Bakhtiyar <[email protected]>

Un-normalised monolingual Sumerian data added to processed-data/

;

f47c338c39a4a8f2cfdc2a0c14950d17870f287f authored over 6 years ago by Bakhtiyar <[email protected]>

Token numbers fix

0a2d86fdf26d120bbd73c9fed04508b7c24e159a authored over 6 years ago by Bakhtiyar <[email protected]>

Short error fix in compression script

1eca583f21970da0e522f44c1cb2794344ca8caa authored over 6 years ago by Bakhtiyar <[email protected]>

SRL compressed for Sumerian - v1.0

e8f96d30d041c76df9b5a54a22731e5c23a3292c authored over 6 years ago by Bakhtiyar <[email protected]>

Compressed projection script added

a5f61ba1272d35b4ba973f180266685f0754a0fb authored over 6 years ago by Bakhtiyar <[email protected]>

Compression algorithm in progress

9bce2e060f81609452bf4e71c208cb6fd78fd463 authored over 6 years ago by Bakhtiyar <[email protected]>

Single line break instead of double newlines

1dfbba8af79372952edd65908db0ec19693e618a authored over 6 years ago by Bakhtiyar <[email protected]>

Updated README to reflect latest scripts

8db36f56bdeb50abada2ddc89b88ac1ff234733e authored over 6 years ago by Bakhtiyar <[email protected]>

Projected SRL tags after removal of non-Sumerian chars.

4c832bebe93c72979cec12665b815be2a6b0c48d authored over 6 years ago by Bakhtiyar <[email protected]>

Remove non-Sumerian characters/words in projection script if alignment does not exist

d9b381223aca044ad5166ed27b1df2ec13774ecf authored over 6 years ago by Bakhtiyar <[email protected]>

Extended projected SRL data onto Sumerian

4aee3180cb0415ec87ed7fe6afdc3765b681ba5f authored over 6 years ago by Bakhtiyar <[email protected]>

Single line fix - double lines b/w each sentence fixed to single

109688cbd27a50d46dba2301bc9764c61ee11233 authored over 6 years ago by Bakhtiyar <[email protected]>

DFS extension of SRL Eng tags added

eabe6129e37214cce76ca36b0600baeb0c3a3d96 authored over 6 years ago by Bakhtiyar <[email protected]>

Underscore fixing in fix-mate-output.py

c63b058b7703cb0d3c360a8dbd83cf7269a4b63e authored over 6 years ago by Bakhtiyar <[email protected]>

Error fixing in fix-mate-output.py

1ab3b268f3670bd3e2fc68daa35618ffbccde525 authored over 6 years ago by Bakhtiyar <[email protected]>

Error fixing in fix-mate-output.py

4a434bdf739092eec352bf3bd0871273b473ace5 authored over 6 years ago by Bakhtiyar <[email protected]>

Error fixing in fix-mate-output.py

23fe30c52cd4444e77b47254573a60223c2913d9 authored over 6 years ago by Bakhtiyar <[email protected]>

Error fixing in fix-mate-output.py

46665df42b7bb0224db865dce1e086c28c10ee20 authored over 6 years ago by Bakhtiyar <[email protected]>

Extended arg SRL Eng tag file added

fb2258f333c79a08fd90469183f77e50dd9bbc5a authored over 6 years ago by Bakhtiyar <[email protected]>

Fix script added for extending semantic arguments for the mate-tools Eng SRL output

3f5245b1235032414b1deb7de9b6381603ff159b authored over 6 years ago by Bakhtiyar <[email protected]>

Doc info added

d830338521170baf5bb4418af19a8c303753b0f6 authored over 6 years ago by Bakhtiyar <[email protected]>

README update

a485c686c99cb10bf95a607688894890ac38a380 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added projection data

4f6d26265392dce805a8b6522156b73e55792676 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modification to projection script

69690e792e3e5ad497464ac15a8baae369c2f9e7 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

CLeaned projections added

00fe5afef77af4cd876aced929012a979385ff68 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

New projected data

0e8ed9145261d57b764f770cc4d51dbc43a46e93 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

New cleaned mate-parsed output after correcting line breaks

9f8f41d9b5f8d799649e42cfe21b9b797451fdea authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Line breaks corrected to their equivalents from the parallel sum-eng version

8298821b8bef1c909a6955a1e7500e44c5a6efc4 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added projected new data after error correction

497324e9e22c11bedb93551e54473df9e1fe3bf4 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Fixed empty blank line in eng-training data from cdli

070fc2910e8580f796995840dec809df8cd41ace authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modified mate-parsing script to reflect output format changes

3582c19207e02ccbdbfdf30490011c9004f77a53 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Updated mate-tools parsed data after correction of Line 2291

cd5cd5517e1bead490a92df6a620d4859d168155 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Merge branch 'master' of https://github.com/cdli-gh/Semantic-Role-Labeler

c714085668f776e61c69b75c67caa9030b5e494e authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Upload test_projected file

bd367eac10015c8f0e5ce18da6be41efb95f65b8 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update REAME

380969e8a9501659e79e58e3ba01ef946798b059 authored over 6 years ago by Bakhtiyar <[email protected]>

Update REAME

7231752040647771611374a25801678045be933f authored over 6 years ago by Bakhtiyar <[email protected]>

Update REAME

ad3b36d3f50519762bd221272682d6f8e9d75d37 authored over 6 years ago by Bakhtiyar <[email protected]>

Added updated projected SRL tag file for Sumerian

4d74389b26a26c3a86634733ea815ba51529850e authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Tab separaed in conll instead of space separation while building output file

4bd68ca80301bf89e0eabf117157d5328cd50dd4 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Error log added

844309b6d79f38b45952a2c56e2ec0bdff73861b authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Updated README.md

abab07704a19ca6f36fe36b73cbbdc21fc469616 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Merge branch 'master' of https://github.com/cdli-gh/Semantic-Role-Labeler

d63b2219e3e29fa86c2df1e2cd81a53559bd7a54 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Projection python script added

4107a3b18576174aefeed6fe6de5e1b722de32e8 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Basic projected SRL tags added

6a13e0aa2c04d757b4e2e6782daffb7ff7b1b91c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update README.md

1a0b71299c3c7cd9b06bdfc370389bbd49487c96 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Word aligned data with new delimiter

381efbc345ec2d8c096ad45a81a9a5056ce679ae authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Changed label_to_word to have a different delimiter '|'

5c91f3b192255d3f8ff6965538c462363e39c7a0 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update README version 2.2

35b4f2614c6230e4d3020c744fdfa65cf084dfdd authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update README version 2.1

086bad181499759a6abad172a59ab691cc1ce3cd authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Updated README - ver 2.0

b6c1b0446a50886d21a0c3f21084a20b255fc520 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Updated README - ver 2.0

91db00bc72af293bcca9e767376ca0bf948626a1 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Updated README - ver 2.0

2d4e4ae1e9ae923bce134b036dda93dc4414c3ad authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Slight reshuffle

f44df64b81b9e42918b3229957e6144ec2b60075 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

README v1.2

ccc334dbad378453ef4b03c7b45076698764454e authored over 6 years ago by Bakhtiyar Syed <[email protected]>

README v1.1

9e79dc7bcd507c8eb8fbefec05257c9e7f007c80 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update README v1.1

06e9273fae24c4d649c8d5e9f7edf435fb6eb6fd authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Restructured files and folders

ea486741dfe1bde25f1f67e3b558fee9135e47f1 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added processed word-alignments(both index-based & word-based) from efmaral

5fd99d712d93405eb09e56f3b46848b98198fcdf authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update script according to requirements

0172f654e07721b9c786ff83428fbd894be02091 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update README.md

e0ad4d9130c95afa5c942f5c59bc6ea2dd58d961 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Error checker for word-aligned data

e301d4f979b09e9a7ba6364802cbfabfc5d857bc authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added word-aligned file

45c826a908efa136c3756625e24e5e620d449e92 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modified error handling

de0870a90a6b5eab793e5c5795d7b656e4e1f4e1 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modified label_to_word.py script

f3daa4967601a2ae583ab6be410eda573d24155c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Fastalign merge script added

60614d7e96840516b2f503aedd0144864226f209 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Unifying script ETCSL - CDLI added

15a9748a24569bc74f9b8403c7308649b4c77f6a authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Slight modifs to data - line 2291 corrected

de1480e8c618a6e194d69f5b8f469b54e14ce4cf authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Labels fast_align to word-level info

d3fbbaa7403318de28a14f7b13f45914a2f6cf43 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Symmetrized word alignments

8fa03cb2198268b082c2bd04d0d84d8b65f1a90b authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added both forward and reverse word alignments for Eng-Sum - via fast-align

7036da9420f563d0cc06249e92f3923ff3184ec8 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Corrections to translated parallel data

37a0c6f04ab865022fabc74323b46f03b763e33d authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Unnormalised data added for parallel translations

bb88201fe1215ee0db9b6b67e12f6f93be50bf19 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modification to unnormalise.py - conversion from $ to |||

93654598be491ec18a7122d05bd5b5917692ab6e authored over 6 years ago by Bakhtiyar Syed <[email protected]>

SRL structure for non-normalised numerical data

6ec842f27699be1da23cded535775a4fcc686f61 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Unnormalised data added

debccf0485944ed42e137db61d81f1940406360c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Unnormalise script written - NUMB and ordNUMB changed to random numerals

df1f274c276b8a01e012feafed40d05db150cdc1 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Minor change

896c40743eec925c403979b1db6096f8e978d8be authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Sample ETCSL mate-tools output for English added - results.out

4d9f5032b15568b64259d990ac4522e5b2433ca3 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Outputs from mate-tools for new CDLI Mtaac corpus added

8fdb2813e61d1c5ab289f7910ccb5fa41853af46 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Resolved mate-tools bug by encoding file via codecs(python 2) to 'utf-8'

266ea6c3f09625fc0d8b86162603e0297cc44494 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Add parallel data from cdli_urIII repository

ace033abf14e1052f93fab161a7da44d4fea1479 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Rename giza++ file dir

d607e7cea3411f69ee9f891bcb7383601d2ca1cf authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Attrib modification

fd9312108291101cdd3ebd4bff9057fa0a58a80e authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Processed etcsl files added - without sectional info

a84266bcd7cbd3362200dcf19bd244f9685d6138 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Update parallel creation file

440993094374447b7dc4710fdb16eb8e08f8d1c9 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modified script to account for different sections

879c263f421e7b4efd1a3e07706f411194747fb0 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added processed files - version 1.0

ee14ee00d0e7fcc6763fd2c7e24d5b04b06e251a authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Parallel creation script added

885e64727bb4e26e4a23e149cbcc6401b4fec229 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Modified script for Etcsl-Eng

eb1119850cd2704aff642cc90106ecc0b2ff245c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Original scraper added

c25e659c25a331965afd5c349b6220dc85f07c8c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Processed ETCSL English data added

3a1ecc3a1717b59753804a31d62eaf0e8c57c1bc authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added processed files of ETCSL sumerian transliterations from XML

cd4e68a3952a3145b6f90d20669e8dbdb2c06fac authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Mate output for phrase segmented data

9aea1385549f1dd1c6f162f6aeb55cb1a7fff00a authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Output from mate-tools stored

dbbd823f53f22d5f49cd9d03cfcf453369003e5c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Mate-tools parsing script added

09d0a29146df83e6538ff6742e9317375d46a0ab authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added SRL on segmented Eng sentences

5a45172b2852bf2918c2f3795b6f6b60d1b08a19 authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Processed segmented data added

622009c1903a1b5e7f2fdc68a0bfe9151490581c authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Added sentence segmentation for Eng-Sum

f8597377e0eec8178113bac822423ad1d99d9d0f authored over 6 years ago by Bakhtiyar Syed <[email protected]>

Ecosyste.ms: OpenCollective

github.com/cdli-gh/Semantic-Role-Labeler