Skip to content

Commit

Permalink
Updated statistics.
Browse files Browse the repository at this point in the history
  • Loading branch information
dan-zeman committed May 5, 2024
1 parent 1851b50 commit 780fc8c
Showing 1 changed file with 24 additions and 23 deletions.
47 changes: 24 additions & 23 deletions stats.xml
Original file line number Diff line number Diff line change
Expand Up @@ -5,26 +5,26 @@
fused is the number of tokens that are split to two or more syntactic words
The words and fused elements can be omitted if no token is split to smaller syntactic words. -->
<size>
<total><sentences>2203</sentences><tokens>26920</tokens><words>57096</words><fused>16827</fused></total>
<train><sentences>1419</sentences><tokens>16860</tokens><words>35764</words><fused>10491</fused></train>
<dev><sentences>381</sentences><tokens>5164</tokens><words>10960</words><fused>3238</fused></dev>
<total><sentences>2203</sentences><tokens>26919</tokens><words>57097</words><fused>16828</fused></total>
<train><sentences>1419</sentences><tokens>16859</tokens><words>35764</words><fused>10492</fused></train>
<dev><sentences>381</sentences><tokens>5164</tokens><words>10961</words><fused>3238</fused></dev>
<test><sentences>403</sentences><tokens>4896</tokens><words>10372</words><fused>3098</fused></test>
</size>
<lemmas unique="2511" /><!-- ⲡ, ⲛ, ⲛⲧⲟϥ, ·, ⲁ, ⲛⲧⲟⲟⲩ, ⲉ, ⲉⲧⲉⲣⲉ, ⲉⲣⲉ, ⲟⲩ, ⲛⲁ, ϩⲛ, ⲁⲛⲟⲕ, ϫⲉ, ⲁⲩⲱ -->
<lemmas unique="2512" /><!-- ⲡ, ⲛ, ⲛⲧⲟϥ, ·, ⲁ, ⲛⲧⲟⲟⲩ, ⲉ, ⲉⲧⲉⲣⲉ, ⲉⲣⲉ, ⲟⲩ, ⲛⲁ, ϩⲛ, ⲁⲛⲟⲕ, ϫⲉ, ⲁⲩⲱ -->
<forms unique="2822" /><!-- ⲛ, ϥ, ·, ⲡ, ⲉ, ⲁ, ⲟⲩ, ⲙ, ⲛⲁ, ⲩ, ϫⲉ, ⲁⲩⲱ, ⲥ, ., ⲧ -->
<fusions unique="9011" /><!-- ⲛⲁϥ, ⲙⲙⲟⲥ, ⲙⲙⲟϥ, ⲉⲣⲟϥ, ⲡⲉϫⲁϥ, ⲙⲡⲛⲟⲩⲧⲉ, ⲛⲁⲩ, ⲛⲧϩⲉ, ⲛⲁⲓ, ⲙⲙⲟⲟⲩ, ⲧⲏⲣⲟⲩ, ⲉϥϫⲱ, ⲛϩⲏⲧϥ, ⲛⲁⲕ, ⲉⲣⲟⲓ -->
<fusions unique="9012" /><!-- ⲛⲁϥ, ⲙⲙⲟⲥ, ⲙⲙⲟϥ, ⲉⲣⲟϥ, ⲡⲉϫⲁϥ, ⲙⲡⲛⲟⲩⲧⲉ, ⲛⲁⲩ, ⲛⲧϩⲉ, ⲛⲁⲓ, ⲙⲙⲟⲟⲩ, ⲧⲏⲣⲟⲩ, ⲉϥϫⲱ, ⲛϩⲏⲧϥ, ⲛⲁⲕ, ⲉⲣⲟⲓ -->
<!-- Statistics of universal POS tags. The comments show the most frequent lemmas. -->
<tags unique="15">
<tag name="ADJ">38</tag><!-- ϣⲏⲙ, ⲕⲁⲑⲟⲗⲓⲕⲏ, ⲕⲟⲩⲓ, ⲟⲩⲱⲧ -->
<tag name="ADP">8354</tag><!-- ⲛ, ⲉ, ϩⲛ, ⲙⲛ, ⲛⲁ, ⲉⲧⲃⲉ, ⲛⲥⲁ, ϩⲓ, ⲉϫⲛ, ϣⲁ -->
<tag name="ADV">2261</tag><!-- ⲉⲃⲟⲗ, ⲁⲛ, ⲉϩⲟⲩⲛ, ⲧⲏⲣ, ⲛ, ⲟⲛ, ⲙⲙⲁⲩ, ⲉϩⲣⲁⲓ, ⲧⲙ, ⲙⲡⲣ -->
<tag name="ADV">1995</tag><!-- ⲉⲃⲟⲗ, ⲁⲛ, ⲉϩⲟⲩⲛ, ⲛ, ⲟⲛ, ⲙⲙⲁⲩ, ⲉϩⲣⲁⲓ, ⲧⲙ, ⲙⲡⲣ, ⲉⲙⲁⲧⲉ -->
<tag name="AUX">3481</tag><!-- ⲁ, ⲛⲁ, ⲛⲧⲉ, ⲛⲧⲉⲣⲉ, ⲛⲉⲣⲉ, ⲙⲡⲉ, ϣⲁⲣⲉ, ⲙⲁⲣⲉ, ϣ, ⲛⲛⲉ -->
<tag name="CCONJ">1347</tag><!-- ⲁⲩⲱ, ⲁⲗⲗⲁ, ⲏ, ⲟⲩⲇⲉ, ϫⲉ, ⲉⲓⲧⲉ, ⲙⲏ, ⲡⲗⲏⲛ, ⲕⲁⲓ, ⲟⲩⲧⲉ -->
<tag name="DET">7375</tag><!-- ⲡ, ⲟⲩ, ⲡⲉϥ, ⲡⲁ, ⲡⲁⲓ, ⲡⲉⲓ, ⲡⲉⲕ, ⲡⲉⲛ, ⲡⲉⲩ, ⲕⲉ -->
<tag name="NOUN">8026</tag><!-- ⲛⲟⲩⲧⲉ, ϩⲉ, ⲣⲱⲙⲉ, ⲙⲁ, ϫⲟⲉⲓⲥ, ⲥⲟⲛ, ϩⲏⲧ, ϩⲱⲃ, ϣⲏⲣⲉ, ⲉⲓⲱⲧ -->
<tag name="NOUN">8292</tag><!-- ⲛⲟⲩⲧⲉ, ϩⲉ, ⲣⲱⲙⲉ, ⲙⲁ, ϫⲟⲉⲓⲥ, ⲥⲟⲛ, ⲧⲏⲣ, ϩⲏⲧ, ϩⲱⲃ, ϣⲏⲣⲉ -->
<tag name="NUM">300</tag><!-- ⲟⲩⲁ, ⲥⲛⲁⲩ, ϣⲉ, ϣⲟⲙⲛⲧ, ⲙⲏⲧ, ⲙⲛⲧⲥⲛⲟⲟⲩⲥ, ⲥⲁϣϥ, ⲧⲃⲁ, ϩⲙⲉ, ⲙⲁⲁⲃ -->
<tag name="PART">2036</tag><!-- ⲇⲉ, ⲉ, ⲉⲣⲉ, ⲅⲁⲣ, ⲛϭⲓ, ϭⲉ, ⲱ, ⲉⲓⲥ, ⲙⲉⲛ, ϩⲁⲙⲏⲛ -->
<tag name="PRON">9354</tag><!-- ⲛⲧⲟϥ, ⲛⲧⲟⲟⲩ, ⲁⲛⲟⲕ, ⲛⲧⲟⲥ, ⲛⲧⲟⲕ, ⲡⲉ, ⲛⲧⲱⲧⲛ, ⲁⲛⲟⲛ, ⲛⲓⲙ, ⲛⲧⲟ -->
<tag name="PRON">9355</tag><!-- ⲛⲧⲟϥ, ⲛⲧⲟⲟⲩ, ⲁⲛⲟⲕ, ⲛⲧⲟⲥ, ⲛⲧⲟⲕ, ⲡⲉ, ⲛⲧⲱⲧⲛ, ⲁⲛⲟⲛ, ⲛⲓⲙ, ⲛⲧⲟ -->
<tag name="PROPN">734</tag><!-- ⲓⲏⲥⲟⲩⲥ, ⲓⲱϩⲁⲛⲛⲏⲥ, ⲃⲟⲉⲥ, ϩⲣⲟⲩⲑ, ⲛⲟⲉⲙⲓⲛ, ⲡⲁⲙⲃⲱ, ⲥⲁⲧⲁⲛⲁⲥ, ⲓⲁⲕⲱⲃ, ⲇⲏⲙⲏⲧⲣⲓⲟⲥ, ⲇⲓⲁⲃⲟⲗⲟⲥ -->
<tag name="PUNCT">3582</tag><!-- ·, ., ,, —, :, ⲻ, ◈, ⁛—, ⁛, ═════ -->
<tag name="SCONJ">3351</tag><!-- ⲉⲧⲉⲣⲉ, ϫⲉ, ⲉⲣⲉ, ϫⲉⲕⲁⲁⲥ, ⲉϣⲱⲡⲉ, ϩⲱⲥ, ϩⲱⲥⲧⲉ, ⲉϣϫⲉ, ⲉⲓⲙⲏⲧⲓ, ⲉⲛⲉ -->
Expand All @@ -33,15 +33,15 @@
</tags>
<!-- Statistics of features and values. The comments show the most frequent word forms. -->
<feats unique="27">
<feat name="Definite" value="Def" upos="ADV,DET,PRON">14795</feat><!-- ϥ, ⲡ, ⲛ, ⲩ, ⲥ, ⲧ, ⲓ, ⲟⲩ, ⲕ, ⲡⲉ -->
<feat name="Definite" value="Def" upos="DET,NOUN,PRON">14795</feat><!-- ϥ, ⲡ, ⲛ, ⲩ, ⲥ, ⲧ, ⲓ, ⲟⲩ, ⲕ, ⲡⲉ -->
<feat name="Definite" value="Ind" upos="DET">947</feat><!-- ⲟⲩ, ϩⲉⲛ, ⲩ -->
<feat name="Foreign" value="Yes" upos="ADJ,ADP,ADV,AUX,CCONJ,DET,NOUN,NUM,PART,PRON,PROPN,SCONJ,VERB,X">4718</feat><!-- ⲇⲉ, ⲅⲁⲣ, ⲁⲗⲗⲁ, ⲏ, ⲓⲏⲥⲟⲩⲥ, ⲭⲣⲓⲥⲧⲟⲥ, ⲓⲱϩⲁⲛⲛⲏⲥ, ⲕⲁⲧⲁ, ⲟⲩⲇⲉ, ⲡⲛⲉⲩⲙⲁ -->
<feat name="Gender" value="Fem" upos="DET,PRON">2380</feat><!-- ⲥ, ⲧ, ⲧⲉ, ⲧⲉϥ, ⲧⲉⲓ, ⲧⲁ, ⲉ, ⲧⲉⲕ, ⲧⲁⲓ, ⲧⲉⲩ -->
<feat name="Gender" value="Masc" upos="DET,PRON">7464</feat><!-- ϥ, ⲡ, ⲡⲉ, ⲕ, ⲡⲁ, ⲡⲉϥ, ⲡⲁⲓ, ⲡⲉⲓ, ⲡⲉⲕ, ⲅ -->
<feat name="Gender" value="Masc" upos="DET,PRON">7465</feat><!-- ϥ, ⲡ, ⲡⲉ, ⲕ, ⲡⲁ, ⲡⲉϥ, ⲡⲁⲓ, ⲡⲉⲓ, ⲡⲉⲕ, ⲅ -->
<feat name="Gender[psor]" value="Fem" upos="DET">124</feat><!-- ⲡⲉⲥ, ⲧⲉⲥ, ⲡⲟⲩ, ⲧⲟⲩ, ⲛⲟⲩ, ⲛⲉⲥ -->
<feat name="Gender[psor]" value="Masc" upos="DET">594</feat><!-- ⲡⲉϥ, ⲛⲉϥ, ⲧⲉϥ, ⲡⲉⲕ, ⲧⲉⲕ, ⲛⲉⲕ, ⲡⲱⲕ, ⲡⲱϥ, ⲛⲟⲩⲕ, ⲧⲱϥ -->
<feat name="Number" value="Plur" upos="DET,PRON">4046</feat><!-- ⲛ, ⲩ, ⲟⲩ, ⲧⲛ, ⲛⲉ, ⲧⲉⲧⲛ, ⲥⲉ, ⲛⲉϥ, ⲛⲁⲓ, ⲛⲁ -->
<feat name="Number" value="Sing" upos="DET,PRON">11781</feat><!-- ϥ, ⲡ, ⲥ, ⲧ, ⲟⲩ, ⲡⲉ, ⲓ, ⲕ, ⲧⲉ, ϩⲉⲛ -->
<feat name="Number" value="Plur" upos="DET,PRON">4045</feat><!-- ⲛ, ⲩ, ⲟⲩ, ⲧⲛ, ⲛⲉ, ⲧⲉⲧⲛ, ⲥⲉ, ⲛⲉϥ, ⲛⲁⲓ, ⲛⲁ -->
<feat name="Number" value="Sing" upos="DET,PRON">11782</feat><!-- ϥ, ⲡ, ⲥ, ⲧ, ⲟⲩ, ⲡⲉ, ⲓ, ⲕ, ⲧⲉ, ϩⲉⲛ -->
<feat name="Number[psor]" value="Plur" upos="DET">331</feat><!-- ⲡⲉⲛ, ⲛⲉⲛ, ⲛⲉⲩ, ⲛⲉⲧⲛ, ⲡⲉⲩ, ⲧⲉⲩ, ⲡⲉⲧⲛ, ⲧⲉⲛ, ⲧⲉⲧⲛ, ⲡⲱⲧⲛ -->
<feat name="Number[psor]" value="Sing" upos="DET">1024</feat><!-- ⲡⲉϥ, ⲡⲁ, ⲛⲉϥ, ⲧⲉϥ, ⲡⲉⲕ, ⲛⲁ, ⲧⲁ, ⲧⲉⲕ, ⲛⲉⲕ, ⲡⲉⲥ -->
<feat name="NumType" value="Card" upos="NUM">300</feat><!-- ⲟⲩⲁ, ⲥⲛⲁⲩ, ϣⲉ, ϣⲟⲙⲛⲧ, ⲙⲛⲧⲥⲛⲟⲟⲩⲥ, ⲙⲏⲧ, ⲥⲁϣϥ, ⲟⲩⲉⲓ, ⲧⲃⲁ, ⲥⲛⲧⲉ -->
Expand All @@ -53,20 +53,20 @@
<feat name="PronType" value="Art" upos="DET">5376</feat><!-- ⲡ, ⲧ, ⲛ, ⲟⲩ, ⲡⲉ, ϩⲉⲛ, ⲧⲉ, ⲛⲉ, ⲕⲉ, ⲩ -->
<feat name="PronType" value="Dem" upos="DET">561</feat><!-- ⲡⲁⲓ, ⲛⲁⲓ, ⲡⲉⲓ, ⲧⲉⲓ, ⲧⲁⲓ, ⲛⲉⲓ, ⲡⲓ, ⲛⲓ, ⲡⲏ, ⲛⲏ -->
<feat name="PronType" value="Ind" upos="PRON">146</feat><!-- ⲛⲓⲙ, ⲟⲩ -->
<feat name="PronType" value="Int" upos="ADV,PRON">189</feat><!-- ⲟⲩ, ⲁϣ, ⲛⲓⲙ, ⲟⲩⲏⲣ, ⲧⲱⲛ, ⲁⲟⲩⲏⲣ, ⲡⲱⲥ -->
<feat name="PronType" value="Prs" upos="ADV,DET,PRON">9909</feat><!-- ϥ, ⲩ, ⲥ, ⲓ, ⲟⲩ, ⲕ, ⲛ, ⲧⲛ, ⲧⲉⲧⲛ, ⲡⲁ -->
<feat name="PronType" value="Int" upos="ADV,PRON">190</feat><!-- ⲟⲩ, ⲁϣ, ⲛⲓⲙ, ⲟⲩⲏⲣ, ⲧⲱⲛ, ⲁⲟⲩⲏⲣ, ⲡⲱⲥ -->
<feat name="PronType" value="Prs" upos="DET,NOUN,PRON">9909</feat><!-- ϥ, ⲩ, ⲥ, ⲓ, ⲟⲩ, ⲕ, ⲛ, ⲧⲛ, ⲧⲉⲧⲛ, ⲡⲁ -->
<feat name="PronType" value="Rcp" upos="NOUN">55</feat><!-- ⲉⲣⲏⲩ -->
<feat name="PronType" value="Tot" upos="ADV">149</feat><!-- ⲧⲏⲣ -->
<feat name="Reflex" value="Yes" upos="ADV,PRON">15</feat><!-- ⲙⲙⲓⲛⲙⲙⲟ, ⲙⲙⲓⲛⲙⲙⲱ -->
<feat name="PronType" value="Tot" upos="NOUN">149</feat><!-- ⲧⲏⲣ -->
<feat name="Reflex" value="Yes" upos="NOUN,PRON">15</feat><!-- ⲙⲙⲓⲛⲙⲙⲟ, ⲙⲙⲓⲛⲙⲙⲱ -->
<feat name="VerbForm" value="Fin" upos="AUX,PRON,VERB">6236</feat><!-- ⲡⲉϫⲁ, ⲉⲓ, ϫⲱ, ϣⲱⲡⲉ, ⲃⲱⲕ, ϫⲟⲟ, ⲛⲁⲩ, ϯ, ⲣ, ⲥⲱⲧⲙ -->
<feat name="VerbForm" value="Inf" upos="VERB">250</feat><!-- ϯ, ⲃⲱⲕ, ⲛⲁⲩ, ⲣ, ϭⲱ, ϫⲓ, ⲁⲁ, ⲕⲁ, ⲧⲁⲙⲟ, ϣⲁϫⲉ -->
</feats>
<!-- Statistics of universal dependency relations. -->
<deps unique="36">
<deps unique="37">
<dep name="acl">9</dep>
<dep name="acl:relcl">1375</dep>
<dep name="advcl">1518</dep>
<dep name="advmod">2908</dep>
<dep name="advmod">2644</dep>
<dep name="amod">39</dep>
<dep name="appos">408</dep>
<dep name="aux">3477</dep>
Expand All @@ -78,20 +78,21 @@
<dep name="cop">500</dep>
<dep name="csubj">144</dep>
<dep name="dep">22</dep>
<dep name="det">7017</dep>
<dep name="det">5273</dep>
<dep name="discourse">75</dep>
<dep name="dislocated">889</dep>
<dep name="expl">3</dep>
<dep name="expl">272</dep>
<dep name="fixed">300</dep>
<dep name="flat">50</dep>
<dep name="iobj">84</dep>
<dep name="mark">4135</dep>
<dep name="nmod">1906</dep>
<dep name="nsubj">5548</dep>
<dep name="nmod:poss">1744</dep>
<dep name="nsubj">5549</dep>
<dep name="nummod">122</dep>
<dep name="obj">2643</dep>
<dep name="obj">2374</dep>
<dep name="obl">4659</dep>
<dep name="obl:npmod">104</dep>
<dep name="obl:npmod">368</dep>
<dep name="orphan">22</dep>
<dep name="parataxis">702</dep>
<dep name="punct">3582</dep>
Expand Down

0 comments on commit 780fc8c

Please sign in to comment.