Language Processing Api
Language Processing api is also Natural Langugage Processing Api
allow you to extract meaningful part of human language by the means of NLP algorithm.
Languages
Currently this api is only supported for ENGLISH
language, but soon we will be adding multiple languages
Endpoint
POST - /ml/language-processing
Parameters
file
- required
- Type:
String text
- Details: english language text is required to extract data.
param
- optional
- Type:
label
,lemma
,pos
,dep
,is_stop
,is_alpha
,is_email
,ent_type
,ent_loc
,morph
- Default: default value is
,
seperated theseent_type,pos,is_stop
- Details: You can pass more than these value by comma separator
remove_stop
- optional
- Type:
true
orfalse
- Default:
false
- Details: Stop words are those words which don't have any particular meaning inside the sentence
Example
Request
curl --form "text=`i used to go for Taj mahal but now i dont go there.`¶ms=label,lemma,pos,dep,is_stop,is_alpha,is_email,ent_type,ent_loc,morph $BASE_ROUTE/ml/language-processing
Info
Here we have passed all the available param type for demo purpose. You can pass according to your need.
Response
{
"data": [
{
"dep": "nsubj",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "I",
"morph": "Case=Nom|Number=Sing|Person=1|PronType=Prs",
"pos": "PRON",
"text": "i"
},
{
"dep": "ROOT",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "use",
"morph": "Tense=Past|VerbForm=Fin",
"pos": "VERB",
"text": "used"
},
{
"dep": "aux",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "to",
"morph": "",
"pos": "PART",
"text": "to"
},
{
"dep": "xcomp",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "go",
"morph": "VerbForm=Inf",
"pos": "VERB",
"text": "go"
},
{
"dep": "prep",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "for",
"morph": "",
"pos": "ADP",
"text": "for"
},
{
"dep": "compound",
"ent_loc": "B",
"ent_type": "GPE",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "Taj",
"morph": "Number=Sing",
"pos": "PROPN",
"text": "Taj"
},
{
"dep": "pobj",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "mahal",
"morph": "Number=Sing",
"pos": "NOUN",
"text": "mahal"
},
{
"dep": "cc",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "but",
"morph": "ConjType=Cmp",
"pos": "CCONJ",
"text": "but"
},
{
"dep": "advmod",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "now",
"morph": "",
"pos": "ADV",
"text": "now"
},
{
"dep": "nsubj",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "I",
"morph": "Case=Nom|Number=Sing|Person=1|PronType=Prs",
"pos": "PRON",
"text": "i"
},
{
"dep": "aux",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "do",
"morph": "Mood=Ind|Tense=Pres|VerbForm=Fin",
"pos": "AUX",
"text": "do"
},
{
"dep": "neg",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "not",
"morph": "",
"pos": "PART",
"text": "nt"
},
{
"dep": "ROOT",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "go",
"morph": "VerbForm=Inf",
"pos": "VERB",
"text": "go"
},
{
"dep": "advmod",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": true,
"label": null,
"lemma": "there",
"morph": "PronType=Dem",
"pos": "ADV",
"text": "there"
},
{
"dep": "punct",
"ent_loc": "O",
"ent_type": "",
"is_alpha": false,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": ".",
"morph": "PunctType=Peri",
"pos": "PUNCT",
"text": "."
}
],
"status": "done"
}
{
"data": [
{
"dep": "compound",
"ent_loc": "B",
"ent_type": "GPE",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "Taj",
"morph": "Number=Sing",
"pos": "PROPN",
"text": "Taj"
},
{
"dep": "pobj",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "mahal",
"morph": "Number=Sing",
"pos": "NOUN",
"text": "mahal"
},
{
"dep": "neg",
"ent_loc": "O",
"ent_type": "",
"is_alpha": true,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": "not",
"morph": "",
"pos": "PART",
"text": "nt"
},
{
"dep": "punct",
"ent_loc": "O",
"ent_type": "",
"is_alpha": false,
"is_email": false,
"is_stop": false,
"label": null,
"lemma": ".",
"morph": "PunctType=Peri",
"pos": "PUNCT",
"text": "."
}
],
"status": "done"
}