Commit 74e6e182 authored by matjaz's avatar matjaz
Browse files

Added new subproject lemmagen with few base widgets.

parent afd5b6b8
......@@ -195,7 +195,8 @@ INSTALLED_APPS_WORKFLOWS_SUB = (
'workflows.weka',
'workflows.cforange',
'workflows.perfeval',
'workflows.mysql'
'workflows.mysql',
'workflows.lemmagen',
#WORKFLOWS_SUBAPP_PLACEHOLDER
)
......
[
{
"pk": 670474768,
"model": "workflows.category",
"fields": {
"uid": "3f47e2a2-682f-4439-9b7c-e67c6506fd67",
"parent": null,
"workflow": null,
"user": null,
"order": 1,
"name": "LemmaGen"
}
},
{
"pk": 143357551,
"model": "workflows.category",
"fields": {
"uid": "44fdf9b8-8259-4a43-8a77-59753b74cacd",
"parent": 670474768,
"workflow": null,
"user": null,
"order": 1,
"name": "Lemmatization"
}
},
{
"pk": 112143617,
"model": "workflows.abstractwidget",
"fields": {
"category": 143357551,
"treeview_image": null,
"name": "Prebuild Lemmatizer",
"is_streaming": false,
"uid": "9796304a-c9dc-4ffe-a721-65c29e846e34",
"interaction_view": "",
"image": null,
"package": "lemmagen",
"static_image": "lemmagen.png",
"post_interact_action": "",
"user": null,
"visualization_view": "",
"action": "lemmagen_construct_prebuild_lemmatizer",
"wsdl_method": "",
"wsdl": "",
"interactive": false,
"has_progress_bar": false,
"order": 1,
"description": "Automatically generated widget from function ConstructPrebuildLemmatizer in package lemmagen. The original function signature: ConstructPrebuildLemmatizer."
}
},
{
"pk": 222876823,
"model": "workflows.abstractinput",
"fields": {
"widget": 112143617,
"name": "Language",
"short_name": "lng",
"uid": "2452e058-506e-6f62-9f45-1d15de5824bb",
"default": "English",
"required": true,
"multi": false,
"parameter_type": "select",
"variable": "language",
"parameter": true,
"order": 1,
"description": "LemmaSharp.LanguagePrebuilt"
}
},
{
"pk": 971860473,
"model": "workflows.abstractoption",
"fields": {
"uid": "d2925cf1-2943-5aa3-6c2b-5b46caa6c3a6",
"abstract_input": 222876823,
"value": "Bulgarian",
"name": "Bulgarian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 562050028,
"model": "workflows.abstractoption",
"fields": {
"uid": "a3505874-906b-da5e-5b90-58178db7381c",
"abstract_input": 222876823,
"value": "Czech",
"name": "Czech (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 738046929,
"model": "workflows.abstractoption",
"fields": {
"uid": "e529c7d6-83b7-9279-ee22-ecdf7295e5bf",
"abstract_input": 222876823,
"value": "English",
"name": "English (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 31386161,
"model": "workflows.abstractoption",
"fields": {
"uid": "16ea0b07-a565-851b-4feb-2f217e49f9f7",
"abstract_input": 222876823,
"value": "Estonian",
"name": "Estonian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 492581273,
"model": "workflows.abstractoption",
"fields": {
"uid": "4fc30fb2-816d-aece-f281-cb5d6cc4fdbf",
"abstract_input": 222876823,
"value": "Persian",
"name": "Persian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 976062185,
"model": "workflows.abstractoption",
"fields": {
"uid": "50278c48-956a-32a2-761e-b5a195e8cf29",
"abstract_input": 222876823,
"value": "French",
"name": "French (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 645392254,
"model": "workflows.abstractoption",
"fields": {
"uid": "08a3121c-4705-cee1-6575-88483a5a7105",
"abstract_input": 222876823,
"value": "Hungarian",
"name": "Hungarian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 490857421,
"model": "workflows.abstractoption",
"fields": {
"uid": "e8d69c6b-b37f-874a-8dbf-714a4fa04279",
"abstract_input": 222876823,
"value": "Macedonian",
"name": "Macedonian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 368788361,
"model": "workflows.abstractoption",
"fields": {
"uid": "ebd5a5b6-3b46-2147-95e5-051633ba43c4",
"abstract_input": 222876823,
"value": "Polish",
"name": "Polish (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 629253816,
"model": "workflows.abstractoption",
"fields": {
"uid": "a5107bb6-d9a8-4103-7ecb-2bc79196c145",
"abstract_input": 222876823,
"value": "Romanian",
"name": "Romanian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 755813253,
"model": "workflows.abstractoption",
"fields": {
"uid": "b68822dc-44c5-0d01-fca7-84a523f0f2f0",
"abstract_input": 222876823,
"value": "Russian",
"name": "Russian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 362172735,
"model": "workflows.abstractoption",
"fields": {
"uid": "6c117cab-06bd-be31-0d15-4ec6b7b5a8a1",
"abstract_input": 222876823,
"value": "Slovak",
"name": "Slovak (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 338426072,
"model": "workflows.abstractoption",
"fields": {
"uid": "4c5b91b6-c056-c693-1ed0-6d8880099cc5",
"abstract_input": 222876823,
"value": "Slovene",
"name": "Slovene (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 844876010,
"model": "workflows.abstractoption",
"fields": {
"uid": "c711244e-ae1e-86b6-536b-c78b3890d4d9",
"abstract_input": 222876823,
"value": "Serbian",
"name": "Serbian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 1058178025,
"model": "workflows.abstractoption",
"fields": {
"uid": "a1e4a3b6-2f0a-1d96-65a5-99cafc66b2b6",
"abstract_input": 222876823,
"value": "Ukrainian",
"name": "Ukrainian (trained on MULTEXT-East v4 resources)"
}
},
{
"pk": 709329936,
"model": "workflows.abstractoption",
"fields": {
"uid": "96e4b2dc-01ba-4565-4d70-329c04a3aa08",
"abstract_input": 222876823,
"value": "EnglishMT",
"name": "EnglishMT (trained on MULTEXT resources)"
}
},
{
"pk": 880770479,
"model": "workflows.abstractoption",
"fields": {
"uid": "616ddeb6-86be-cf89-c5ff-0b04df7d3235",
"abstract_input": 222876823,
"value": "FrenchMT",
"name": "FrenchMT (trained on MULTEXT resources)"
}
},
{
"pk": 358351563,
"model": "workflows.abstractoption",
"fields": {
"uid": "d4fa9df0-c5b4-bd05-10ff-50243773b89e",
"abstract_input": 222876823,
"value": "German",
"name": "German (trained on MULTEXT resources)"
}
},
{
"pk": 352301260,
"model": "workflows.abstractoption",
"fields": {
"uid": "959c9cdb-aa93-7600-a08f-e1c8d9a63400",
"abstract_input": 222876823,
"value": "Italian",
"name": "Italian (trained on MULTEXT resources)"
}
},
{
"pk": 721366577,
"model": "workflows.abstractoption",
"fields": {
"uid": "3119b7e0-e42e-17ab-dd29-4b7678a46402",
"abstract_input": 222876823,
"value": "Spanish",
"name": "Spanish (trained on MULTEXT resources)"
}
},
{
"pk": 810525562,
"model": "workflows.abstractoutput",
"fields": {
"widget": 112143617,
"name": "LemmaGen Lemmatizer",
"short_name": "lmz",
"variable": "lemamtizer",
"uid": "24208d82-d047-9bea-4091-0bf9ab47f69e",
"order": 1,
"description": ""
}
},
{
"pk": 862594096,
"model": "workflows.abstractwidget",
"fields": {
"category": 143357551,
"treeview_image": null,
"name": "Empty Lemmatizer",
"is_streaming": false,
"uid": "2f4a3645-673c-4b91-bd66-216d092df23f",
"interaction_view": "",
"image": null,
"package": "lemmagen",
"static_image": "lemmagen.png",
"post_interact_action": "",
"user": null,
"visualization_view": "",
"action": "lemmagen_construct_lemmatizer",
"wsdl_method": "",
"wsdl": "",
"interactive": false,
"has_progress_bar": false,
"order": 2,
"description": "Automatically generated widget from function ConstructLemmatizer in package lemmagen. The original function signature: ConstructLemmatizer."
}
},
{
"pk": 418880431,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Use From In Rules",
"short_name": "bol",
"uid": "728f879e-491d-fd9d-8565-5ad4c409e5de",
"default": "true",
"required": false,
"multi": false,
"parameter_type": "checkbox",
"variable": "useFromInRules",
"parameter": true,
"order": 1,
"description": "True if from string should be included in rule identifier ([from]->[to]). False if just length of from string is used ([#len]->[to])."
}
},
{
"pk": 656009326,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Msd Consideration",
"short_name": "msd",
"uid": "46ed84fe-644e-502c-c8b2-cee449185b91",
"default": "Distinct",
"required": false,
"multi": false,
"parameter_type": "select",
"variable": "msdConsider",
"parameter": true,
"order": 2,
"description": "Specification how algorithm considers msd tags."
}
},
{
"pk": 101086762,
"model": "workflows.abstractoption",
"fields": {
"uid": "d902c599-57b2-f31b-5745-5b33e6cb9885",
"abstract_input": 656009326,
"value": "Ignore",
"name": "Ignore (Completely ignores mds tags - join examples with different tags and sum their weihgts)"
}
},
{
"pk": 430658844,
"model": "workflows.abstractoption",
"fields": {
"uid": "5f9232e6-9ffd-930f-5052-e3aac75d5758",
"abstract_input": 656009326,
"value": "Distinct",
"name": "Distinct (Same examples with different msd's are not considered equal and joined)"
}
},
{
"pk": 750614859,
"model": "workflows.abstractoption",
"fields": {
"uid": "8e8cfc28-07c8-f676-63d2-7dbcbf26b1d4",
"abstract_input": 656009326,
"value": "JoinAll",
"name": "JoinAll (Joins examples with different tags - concatenates all msd tags)"
}
},
{
"pk": 524423716,
"model": "workflows.abstractoption",
"fields": {
"uid": "19b7e352-6d87-edea-93ae-3c88885ade7d",
"abstract_input": 656009326,
"value": "JoinDistinct",
"name": "JoinDistinct (Joins examples with different tags - concatenates just distinct msd tags - somehow slower)"
}
},
{
"pk": 486368124,
"model": "workflows.abstractoption",
"fields": {
"uid": "60549577-cfdd-b845-f7d1-c8fd0209423d",
"abstract_input": 656009326,
"value": "JoinSameSubstring",
"name": "JoinSameSubstring (Joins examples with different tags - new tag is the left to right substring that all joined examples share)"
}
},
{
"pk": 741564781,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Max Rules Per Node",
"short_name": "bol",
"uid": "edb3b6c7-aed0-7644-b805-740e4a43ae0e",
"default": "0",
"required": false,
"multi": false,
"parameter_type": "text",
"variable": "maxRulesPerNode",
"parameter": true,
"order": 3,
"description": "How many of the best rules are kept in memory for each node. Zero means unlimited."
}
},
{
"pk": 571211926,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Build Front Lemmatizer",
"short_name": "bol",
"uid": "ff32090f-5cb7-ec11-ada4-060669d1beb5",
"default": "false",
"required": false,
"multi": false,
"parameter_type": "checkbox",
"variable": "buildFrontLemmatizer",
"parameter": true,
"order": 4,
"description": "True: build proccess uses few more hevristics to build first left to right lemmatizer (lemmatizes front of the word); False: (default) do not create additional front lemmatizer;"
}
},
{
"pk": 167197124,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Store All Full Known Words",
"short_name": "bol",
"uid": "d506a033-baa6-ced4-9e77-bbfc5f848655",
"default": "false",
"required": false,
"multi": false,
"parameter_type": "checkbox",
"variable": "storeAllFullKnownWords",
"parameter": true,
"order": 5,
"description": "True: the model will store all known words in full -> the same as having lexicon to check each word before using lemmatizer and then use the lemmatizer only for unknown words; False: (default) the model will try to mimimize the size and will store the full forms of words only in the case if they add new knowledge;"
}
},
{
"pk": 82952051,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Use Msd Split Tree Optimization",
"short_name": "bol",
"uid": "f7fbaba1-ca7e-11e5-ea4a-d052b3380b0f",
"default": "false",
"required": false,
"multi": false,
"parameter_type": "checkbox",
"variable": "useMsdSplitTreeOptimization",
"parameter": true,
"order": 6,
"description": "This is advanced functionality, read the manual."
}
},
{
"pk": 213375530,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Msd specification String",
"short_name": "str",
"uid": "8c7d3609-c428-1b47-ad6c-1d36b0d2c2ca",
"default": "",
"required": false,
"multi": false,
"parameter_type": "textarea",
"variable": "msdSpec",
"parameter": true,
"order": 7,
"description": "This is advanced functionality, read the manual."
}
},
{
"pk": 849902915,
"model": "workflows.abstractinput",
"fields": {
"widget": 862594096,
"name": "Example List",
"short_name": "lst",
"uid": "7d8677e9-65eb-cfc3-ed37-18184ea1e0d1",
"default": "",
"required": false,
"multi": false,
"parameter_type": "text",
"variable": "exampleList",
"parameter": false,
"order": 8,
"description": "List of lemmatization examples which are used for initial lemmatizer training."
}
},
{
"pk": 423204809,
"model": "workflows.abstractoutput",
"fields": {
"widget": 862594096,
"name": "LemmaGen Lemmatizer",
"short_name": "lmz",
"variable": "lemmatizer",
"uid": "b5c40a94-0934-8b9b-13e9-b8cf677fc4ae",
"order": 1,
"description": ""
}
},
{
"pk": 34232932,
"model": "workflows.abstractwidget",
"fields": {
"category": 143357551,
"treeview_image": null,
"name": "Lemmatizer",
"is_streaming": false,
"uid": "3c8148d6-54a6-4d5a-9c24-7be671e95f29",
"interaction_view": "",
"image": null,
"package": "lemmagen",
"static_image": "lemmagen.png",
"post_interact_action": "",
"user": null,
"visualization_view": "",
"action": "lemmagen_lemmatize_words",
"wsdl_method": "",
"wsdl": "",
"interactive": false,
"has_progress_bar": false,
"order": 3,
"description": "Automatically generated widget from function LemmatizeWords in package lemmagen. The original function signature: LemmatizeWords."
}
},
{
"pk": 566085476,
"model": "workflows.abstractinput",
"fields": {
"widget": 34232932,
"name": "Trained Lemmatizer",
"short_name": "lmz",
"uid": "ee0eda9c-7387-7ea0-2145-2f7a9b8ee164",
"default": "",
"required": true,
"multi": false,
"parameter_type": "text",
"variable": "lemmatizer",
"parameter": false,
"order": 1,
"description": "Latino.TextMining.IStemmer"
}
},
{
"pk": 349847221,
"model": "workflows.abstractinput",
"fields": {
"widget": 34232932,
"name": "Word(s)",
"short_name": "wrd",
"uid": "cd08ca1e-be3a-1f14-50a8-70414e21c2ef",