Add Orchid to Universal Dependencies

PyThaiNLP · Mar 25, 2019 · 166b671 · 166b671
1 parent 83bd035
commit 166b671
Showing 1 changed file with 106 additions and 4 deletions.
diff --git a/pythainlp/tag/__init__.py b/pythainlp/tag/__init__.py
@@ -11,6 +11,100 @@
 ]
 from .locations import tag_provinces
 
+# tag map for orchid to Universal Dependencies
+# from Korakot Chaovavanich 
+_TAG_MAP_UD = {
+    #NOUN
+    "NOUN":"NOUN",
+    "NCMN":"NOUN",
+    "NTTL":"NOUN",
+    "CNIT":"NOUN",
+    "CLTV":"NOUN",
+    "CMTR":"NOUN",
+    "CFQC":"NOUN",
+    "CVBL":"NOUN",
+    # VERB
+    "VACT":"VERB",
+    "VSTA":"VERB",
+    #PRON
+    "PRON":"PRON",
+    "NPRP":"PRON",
+    # ADJ
+    "ADJ": "ADJ",
+    "NONM": "ADJ",
+    "VATT": "ADJ",
+    "DONM": "ADJ",
+    # ADV
+    "ADV": "ADV",
+    "ADVN": "ADV",
+    "ADVI": "ADV",
+    "ADVP": "ADV",
+    "ADVS": "ADV",
+	# INT
+    "INT": "INTJ",
+    # PRON
+    "PROPN":"PROPN",
+    "PPRS":"PROPN",
+    "PDMN":"PROPN",
+    "PNTR":"PROPN",
+    # DET
+    "DET": "DET",
+    "DDAN": "DET",
+    "DDAC": "DET",
+    "DDBQ": "DET",
+    "DDAQ": "DET",
+    "DIAC": "DET",
+    "DIBQ": "DET",
+    "DIAQ": "DET",
+    "DCNM": "DET",
+    # NUM
+    "NUM": "NUM",
+    "NCNM": "NUM",
+    "NLBL": "NUM",
+    "DCNM": "NUM",
+	# AUX
+    "AUX": "AUX",
+    "XVBM": "AUX",
+    "XVAM": "AUX",
+    "XVMM": "AUX",
+    "XVBB": "AUX",
+    "XVAE": "AUX",
+	# ADP
+    "ADP": "ADP",
+    "RPRE": "ADP",
+    # CCONJ
+    "CCONJ":"CCONJ",
+    "JCRG":"CCONJ",
+	# SCONJ
+    "SCONJ":"SCONJ",
+    "PREL":"SCONJ",
+    "JSBR":"SCONJ",
+    "JCMP":"SCONJ",
+    # PART
+    "PART":"PART",
+    "FIXN":"PART",
+    "FIXV":"PART",
+    "EAFF":"PART",
+    "EITT":"PART",
+    "AITT":"PART",
+    "NEG":"PART",
+    # PUNCT
+    "PUNCT":"PUNCT",
+    "PUNC":"PUNCT"
+}
+
+def _UD_Exception(w,tag):
+	if w=="การ" or w=="ความ":
+		return "NOUN"
+	return tag
+
+def _orchid_to_ud(tag):
+	_i=0
+	temp=[]
+	while _i<len(tag):
+		temp.append((tag[_i][0],_UD_Exception(tag[_i][0],_TAG_MAP_UD[tag[_i][1]])))
+		_i+=1
+	return temp
 
 def pos_tag(words, engine="perceptron", corpus="orchid"):
     """
@@ -22,10 +116,15 @@ def pos_tag(words, engine="perceptron", corpus="orchid"):
         * perceptron - perceptron tagger (default)
         * artagger - RDR POS tagger
     :param str corpus:
-        * orchid - annotated Thai academic articles
+        * orchid - annotated Thai academic articles (default)
+        * orchid_ud - annotated Thai academic articles using Universal Dependencies Tags
         * pud - Parallel Universal Dependencies (PUD) treebanks
     :return: returns a list of labels regarding which part of speech it is
     """
+    _corpus=corpus
+    _tag=[]
+    if corpus=="orchid_ud":
+        corpus="orchid"
     if not words:
         return []
 
@@ -44,8 +143,10 @@ def tag_(words, corpus=None):
 
     else:  # default, use "unigram" ("old") engine
         from .unigram import tag as tag_
-
-    return tag_(words, corpus=corpus)
+    _tag= tag_(words, corpus=corpus)
+    if _corpus=="orchid_ud":
+        _tag=_orchid_to_ud(_tag)
+    return _tag
 
 
 def pos_tag_sents(sentences, engine="perceptron", corpus="orchid"):
@@ -58,7 +159,8 @@ def pos_tag_sents(sentences, engine="perceptron", corpus="orchid"):
         * perceptron - perceptron tagger (default)
         * artagger - RDR POS tagger
     :param str corpus:
-        * orchid - annotated Thai academic articles
+        * orchid - annotated Thai academic articles (default)
+        * orchid_ud - annotated Thai academic articles using Universal Dependencies Tags
         * pud - Parallel Universal Dependencies (PUD) treebanks
     :return: returns a list of labels regarding which part of speech it is
     """