UCREL · apmoore1 · Nov 15, 2021 · Nov 16, 2021 · Nov 17, 2021 · Nov 17, 2021
diff --git a/Chinese/generated_pos_tagset.tsv b/Chinese/generated_pos_tagset.tsv
@@ -0,0 +1,20 @@
+POS	Count
+noun	47450
+num	900
+pron	356
+pnoun	8904
+adv	5971
+verb	31412
+det	411
+loc	371
+conj	428
+msr	763
+part	3778
+adj	9494
+prep	1614
+intj	272
+mark	192
+idiom	10
+fw	15
+ono	1
+punc	144
diff --git a/Czech/generated_pos_tagset.tsv b/Czech/generated_pos_tagset.tsv
@@ -0,0 +1,12 @@
+POS	Count
+j	71
+v	6050
+r	66
+p	54
+d	1774
+c	58
+n	13057
+a	6670
+t	67
+i	61
+x	233
diff --git a/Dutch/generated_pos_tagset.tsv b/Dutch/generated_pos_tagset.tsv
@@ -0,0 +1,12 @@
+POS	Count
+adj	769
+noun	2061
+verb	1000
+conj	33
+interj	21
+prep	33
+adv	208
+num	39
+pron	53
+intj	1
+art	2
diff --git a/Dutch/simplified-pos-tagset-dut.txt b/Dutch/simplified-pos-tagset-dut.txt
@@ -10,6 +10,5 @@ conj	conjuction
 art	article
 pron	pronoun
 punc	puctuation
-sent	sentence marker
 
 
diff --git a/Finnish/generated_pos_tagset.tsv b/Finnish/generated_pos_tagset.tsv
@@ -0,0 +1,16 @@
+POS	Count
+code	15
+abbrev	409
+proper	7931
+noun	26666
+comppart	608
+adjective	3395
+verb	3365
+interjection	86
+adverb	3243
+preposition	224
+conjunction	116
+numeral	91
+pronoun	73
+noun 	3
+adverb 	1
diff --git a/French/generated_pos_tagset.tsv b/French/generated_pos_tagset.tsv
@@ -0,0 +1,11 @@
+POS	Count
+prep	60
+noun	1633
+adv	147
+verb	448
+adj	264
+det	86
+pron	56
+conj	20
+null	2
+intj	8
diff --git a/Italian/generated_pos_tagset.tsv b/Italian/generated_pos_tagset.tsv
@@ -0,0 +1,15 @@
+POS	Count
+abr	114
+noun	22272
+verb	11056
+null	12
+pnoun	417
+adj	8153
+num	59
+prep	3130
+conj	181
+adv	1405
+pron	366
+intj	73
+art	659
+punc	2
diff --git a/Portuguese/generated_pos_tagset.tsv b/Portuguese/generated_pos_tagset.tsv
@@ -0,0 +1,13 @@
+POS	Count
+num	57
+pnoun	320
+adj	3428
+noun	9291
+verb	3096
+prep	1131
+adv	681
+intj	38
+pron	132
+conj	83
+det	289
+punc	28
diff --git a/README.md b/README.md
@@ -340,6 +340,33 @@ Number of unique values in lexicon file 2 7637
 Number of unique values in common between the two files:3169
 ```
 
+### Create Pos Tagsets
+
+The script creates a POS tagset per language stated within the [./language_resources.json](./language_resources.json) meta data file, which is explained in the [USAS Lexicon Meta Data section](#usas-lexicon-meta-data), and creates a POS tagset based on the POS tags used within the language's single and MWE semantic lexicon files. The POS tagset generated is then saved within each language's folder under the file name `generated_pos_tagset.tsv`. Each generated tagset has two fields `POS`, and `Count`, the `POS` field represents the POS tags, and the `Count` represents the number of times the associated tag has been used within the language's lexicon file(s). An example of this generated POS tagset is shown below, taken from the Welsh language folder:
+
+``` tsv
+POS	Count
+verb	130197
+adv	123
+art	7
+conj	87
+pron	67
+prep	293
+noun	4358
+pnoun	6572
+adj	1542
+fw	40
+num	36
+intj	6
+*	2
+```
+
+To run this script:
+
+``` bash
+python create_pos_tagsets.py
+```
+
 ### Python Requirements
 
 This has been tested with Python >= `3.7`, to install the relevant python requirements:

diff --git a/Russian/generated_pos_tagset.tsv b/Russian/generated_pos_tagset.tsv
@@ -0,0 +1,19 @@
+POS	Count
+fw	6
+intj	13
+s	21003
+a	1931
+adv	171
+conj	17
+v	1701
+part	26
+pr	39
+a-pro	26
+com	4
+parenth	14
+a-num	37
+num	41
+praedic	17
+adv-pro	30
+s-pro	17
+*	1772
diff --git a/Spanish/generated_pos_tagset.tsv b/Spanish/generated_pos_tagset.tsv
@@ -0,0 +1,48 @@
+POS	Count
+noun	2217
+prep	95
+num/noun	52
+pnoun	19993
+adv	238
+adj	947
+verb	717
+conj	37
+intj	3
+prep+art	2
+adj/noun	36
+pron	72
+verb/adj	2
+num	22
+adj/num/noun	13
+adj/nun	1
+num/adj	16
+adj/num	10
+adv/conj	2
+verb/adj/noun	1
+art	67
+verbo	1
+abbr	1
+abbr/noun	1
+prefix	1
+noun/adj	15
+verb + pron	1
+det	1
+noun/adv	1
+adv/adj	1
+adj/adv	1
+adj/pron	7
+verb/noun	6
+con/adj/pron	1
+noun/verb	2
+adj/nm	1
+adv/pron	1
+fw	7
+noun 	1
+noun/num	1
+num/art	1
+art/art/pron	1
+num/art/pron	2
+art/pron	2
+num/adj/pron	1
+noun/pnoun	1
+port	10
diff --git a/Swedish/generated_pos_tagset.tsv b/Swedish/generated_pos_tagset.tsv
@@ -0,0 +1,19 @@
+POS	Count
+nn	9120
+pp	77
+in	25
+vb	2959
+av	3294
+ab	424
+pm	60
+	1860
+prefix	63
+pn	87
+sn	16
+pres part	7
+kn	19
+nl	41
+ie	1
+al	3
+nna	2
+pma	24
diff --git a/Urdu/generated_pos_tagset.tsv b/Urdu/generated_pos_tagset.tsv
@@ -0,0 +1,99 @@
+POS	Count
+at	1
+io	1
+cc	4
+at1	3
+rp	21
+to	2
+pph1	1
+vbz	1
+vbdz	1
+ppis1	1
+rg	12
+ppy	1
+pphs1	2
+iw	1
+ii	13
+vbr	2
+xx	1
+vhz	3
+rr	141
+vhn	1
+pphs2	1
+pp$	1
+ddq	2
+ppis2	1
+vbdr	1
+vd0	1
+vbn	1
+appge	5
+vm	8
+rl	28
+vv0	557
+csw	2
+vvn	99
+pnqs	1
+pn1	13
+ppho2	1
+rrq	6
+ppho1	1
+rt	9
+mc	9
+vdd	1
+uh	16
+ppio1	1
+nn1	423
+rrr	12
+dd2	2
+jj	147
+csn	1
+da2	3
+nnt2	6
+vh0	1
+vbg	1
+da	3
+nnt1	13
+vdz	1
+vbm	2
+ppio2	1
+nn	16
+rrqv	1
+dd1	1
+rrt	6
+nnb	2
+ra	5
+vvd	39
+ge	1
+ja	1
+nn2	93
+cs	4
+md	3
+vvz	40
+vdn	1
+vhg	1
+np1	60
+jb	30
+nnl1	17
+ppx1	5
+vdg	1
+vvg	21
+nno	4
+ppx2	1
+vvi	9
+ddqge	1
+nnu	1
+nnl2	1
+nd1	4
+npm1	12
+jjr	5
+nnu2	3
+pnqo	1
+np2	2
+nn11	1
+npd1	4
+pn	1
+jj%	3
+vvn@	1
+vmk	1
+jjt	2
+nno2	1
diff --git a/Welsh/generated_pos_tagset.tsv b/Welsh/generated_pos_tagset.tsv
@@ -0,0 +1,14 @@
+POS	Count
+verb	130197
+adv	123
+art	7
+conj	87
+pron	67
+prep	293
+noun	4358
+pnoun	6572
+adj	1542
+fw	40
+num	36
+intj	6
+*	2