This is part of archived UD v1 documentation. See http://universaldependencies.org/ for the current version.
home et/pos issue tracker

PROPN: proper noun

Definition

A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object.
Acronyms of proper nouns, such as NATO, are tagged as abbreviated nouns NOUN Abbr=Yes in Estonian UD v 1.3.

Treebank Statistics (UD_Estonian)

There are 3952 PROPN lemmas (14%), 5220 PROPN types (10%) and 13084 PROPN tokens (6%). Out of 15 observed tags, the rank of PROPN is: 3 in number of lemmas, 4 in number of types and 7 in number of tokens.

The 10 most frequent PROPN lemmas: eesti, Tallinn, Euroopa, Tartu, Jan, Peeter, Vene_maa, Hiina, soome, vene

The 10 most frequent PROPN types: Eesti, Eestis, Euroopa, Tartu, Tallinna, Peeter, Jan, Vene, Soome, Venemaa

The 10 most frequent ambiguous lemmas: eesti (ADJ 95, PROPN 19), soome (ADJ 9, PROPN 1), vene (ADJ 32, PROPN 3, NOUN 2), saksa (PROPN 24, ADJ 17), Uus_põld (PROPN 34, NOUN 1), Ken (PROPN 27, NOUN 1), Suur (PROPN 26, NOUN 1), poola (ADJ 3, PROPN 1), balti (PROPN 5, ADJ 2), Posti_mees (PROPN 18, NOUN 1)

The 10 most frequent ambiguous types: Eesti (PROPN 576, ADJ 11), Vene (PROPN 75, NOUN 3), Soome (PROPN 67, ADJ 1), saksa (ADJ 16, PROPN 1), Kala (PROPN 38, NOUN 1), Uuspõld (PROPN 23, NOUN 1), Hollandi (PROPN 22, ADJ 1), New (PROPN 15, NOUN 1), Rüütel (PROPN 15, NOUN 1), Kalju (PROPN 14, NOUN 1)

Morphology

The form / lemma ratio of PROPN is 1.320850 (the average of all parts of speech is 1.839644).

The 1st highest number of forms (10) was observed with the lemma “Eesti”: EESTI, Eesti, Eestiga, Eestil, Eestile, Eestis, Eestiski, Eestisse, Eestist, Eestit.

The 2nd highest number of forms (8) was observed with the lemma “Jan”: Jan, Jane, Jani, Janiga, Janiks, Janil, Janile, Janilt.

The 3rd highest number of forms (8) was observed with the lemma “Rootsi”: Rootsi, Rootsiga, Rootsil, Rootsile, Rootsilt, Rootsis, Rootsist, Rootsit.

PROPN occurs with 4 features: Case (12968; 99% instances), Number (12968; 99% instances), Abbr (107; 1% instances), Hyph (24; 0% instances)

PROPN occurs with 19 feature-value pairs: Abbr=Yes, Case=Abe, Case=Abl, Case=Add, Case=Ade, Case=All, Case=Com, Case=Ela, Case=Ess, Case=Gen, Case=Ill, Case=Ine, Case=Nom, Case=Par, Case=Ter, Case=Tra, Hyph=Yes, Number=Plur, Number=Sing

PROPN occurs with 30 feature combinations. The most frequent feature combination is Case=Nom|Number=Sing (6389 tokens). Examples: Peeter, Jan, Eesti, Tõnu, Ott, Jüri, Jooga, Mart, Ernesaks, Indrikson

Relations

PROPN nodes are attached to their parents using 20 different relations: nmod (6122; 47% instances), nsubj (2688; 21% instances), name (1976; 15% instances), conj (986; 8% instances), dobj (357; 3% instances), root (270; 2% instances), nsubj:cop (261; 2% instances), parataxis (145; 1% instances), amod (72; 1% instances), advcl (70; 1% instances), foreign (49; 0% instances), vocative (28; 0% instances), list (20; 0% instances), xcomp (11; 0% instances), appos (9; 0% instances), dep (6; 0% instances), ccomp (5; 0% instances), case (4; 0% instances), acl:relcl (3; 0% instances), compound (2; 0% instances)

Parents of PROPN nodes belong to 15 different parts of speech: VERB (4614; 35% instances), NOUN (4403; 34% instances), PROPN (3191; 24% instances), ADJ (448; 3% instances), ROOT (270; 2% instances), PRON (49; 0% instances), NUM (46; 0% instances), ADV (31; 0% instances), X (11; 0% instances), AUX (8; 0% instances), SYM (7; 0% instances), CONJ (3; 0% instances), ADP (1; 0% instances), INTJ (1; 0% instances), PUNCT (1; 0% instances)

8938 (68%) PROPN nodes are leaves.

1910 (15%) PROPN nodes have one child.

1289 (10%) PROPN nodes have two children.

947 (7%) PROPN nodes have three or more children.

The highest child degree of a PROPN node is 19.

Children of PROPN nodes are attached using 30 different relations: name (1977; 23% instances), punct (1348; 16% instances), conj (978; 12% instances), appos (941; 11% instances), nmod (760; 9% instances), cc (651; 8% instances), advmod (304; 4% instances), nummod (274; 3% instances), case (272; 3% instances), amod (212; 3% instances), acl (172; 2% instances), acl:relcl (159; 2% instances), parataxis (80; 1% instances), mark (64; 1% instances), foreign (53; 1% instances), det (52; 1% instances), cop (37; 0% instances), nsubj:cop (35; 0% instances), list (23; 0% instances), dep (18; 0% instances), cc:preconj (16; 0% instances), advcl (12; 0% instances), dobj (11; 0% instances), discourse (8; 0% instances), nmod:poss (7; 0% instances), nsubj (4; 0% instances), compound (3; 0% instances), xcomp (2; 0% instances), advmod:quant (1; 0% instances), vocative (1; 0% instances)

Children of PROPN nodes belong to 14 different parts of speech: PROPN (3191; 38% instances), NOUN (1592; 19% instances), PUNCT (1348; 16% instances), CONJ (631; 7% instances), ADJ (389; 5% instances), ADV (341; 4% instances), NUM (279; 3% instances), ADP (269; 3% instances), VERB (227; 3% instances), PRON (94; 1% instances), SCONJ (65; 1% instances), SYM (24; 0% instances), X (17; 0% instances), INTJ (8; 0% instances)

PROPN in other languages: [bg] [cs] [de] [el] [en] [es] [eu] [fa] [fi] [fr] [ga] [he] [hu] [it] [ja] [ko] [sv] [u]