commit f7819831cada26cd9ad47d3d491557da1fad779c
Author: Ifeanyijasper <ifeanyijasper11@gmail.com>
Date:   Sun Jun 20 00:15:21 2021 +0100

    categorise wikipedia corpus

diff --git a/apertium-ibo.ibo.lexd b/apertium-ibo.ibo.lexd
index 4ceba20..6970bac 100644
--- a/apertium-ibo.ibo.lexd
+++ b/apertium-ibo.ibo.lexd
@@ -73,23 +73,24 @@ LEXICON V-Affixes(3)
  LEXICON Nouns
 #=============#
 
-nnà:nnà # "father"
+nna:nna # "father"
 nne:nne   # "mother"
-nwanyi:nwanyi  # "woman"
+nwanyị:nwanyị # "woman"
 nwoke:nwoke   # "man"
 nwa-nwoke:nwa-nwoke  # "boy"
 nwa-nwoke:nwa-nwaanyi # "girl"
 nwa-okoro:nwa-okoro   # "son"
 nwa-agbọghọ:nwa-agbọghọ  # "daughter"
 nwa:nwa   # "child"
-ụmụaka:ụmụaka 	# "children"
+ụmụ:ụmụ 	# "children"
 nwanne-nwaanyi:nwanne-nwaanyi  # "sister"
 nwanne-nwoke:nwanne-nwoke    	# "brother"
-ndị-mmadụ:ndị-mmadụ   # "people"
+ndị\ mmadụ:ndị\ mmadụ   # "people"
 di:di  # "husband"
 nwunye:nwunye # "wife"
 amadi:amadi # "gentleman"
 nwada:nwada # "lady"
+mmadụ:mmadụ # "someone"
 imi:imi   # "nose"
 ire:ire   # "tongue"
 afo:afo   # "stomach"
@@ -186,7 +187,7 @@ anwụ:anwụ	# "wasp"
 okpo:okpo	# "worm"
 ututu:ututu   # "morning"
 abali:abali   # "night"
-onwa:onwa   # "month"
+ọnwa:ọnwa   # "months"
 ugwu:ugwu   # "mountain"
 ahihia:ahihia   # "grass"
 anụmanụ:anụmanụ     # "animal"
@@ -211,7 +212,7 @@ ohia:ohia   # "forest"
 ọkụkụ:ọkụkụ   # "plant"
 abu:abu   # "song"
 achịcha:achịcha   # "bread"
-afa:afa   # "name"
+aha:aha   # "name"
 afịa:afịa   # "market"
 agbọ:agbọ   # "bond"
 ago:ago   # "defense"
@@ -226,6 +227,7 @@ akwa:akwa   # "cloth"
 uwe:uwe   # "shirt"
 akwụkwọ:akwụkwọ   # "book"
 alaka:alaka   # "branch"
+egwu:egwu # "fright"
 anụ:anụ   # "meat"
 arọ:arọ   # "arrow"
 bọta:bọta   # "butter"
@@ -245,6 +247,7 @@ isi:isi   # "odor"
 ite:ite   # "pot"
 iyi:iyi   # "stream"
 kọfị:kọfị   # "coffee"
+ụda:ụda   # "sound"
 mbà:mbà   # "depression"
 mbido:mbido   # "origin"
 mkpisi:mkpisi   # "stick"
@@ -271,10 +274,36 @@ taa:taa   # "tar"
 ube:ube   # "spear"
 ugbo:ugbo   # "vehicle"
 ụra:ụra   # "sleep"
-na-ehi-ụra:na-ehi-ụra     # "sleeping"
+na-ehi\ ụra:na-ehi\ ụra     # "sleeping"
 usoro:usoro   # "format"
 egwuregwu:egwuregwu   # "game"
 n'ime:n'ime   # "inside"
+ebe:ebe   # "place"
+nkiri:nkiri  # "theater"
+ụbọchị:ụbọchị  # "day"
+n'afọ:n'afọ  # "year"
+Naịjirịa:Naịjirịa   # "Nigeria"
+Mahadum:Mahadum  # "university"
+akụkọ:akụkọ   # "story"
+Lagos:Lagos   # "lagos"
+agha:agha    # "war"
+ọchịchị:ọchịchị  # "government"
+ndọrọ\ ndọrọ\ ọchịchị:ndọrọ\ ndọrọ\ ọchịchị
+ego:ego  # "money"
+ozi:ozi  # "message"
+ọrịa:ọrịa  # "disease"
+iwu:iwu  # "law"
+onwe:onwe  # "self"
+okwu:okwu   # "speech"
+ji:ji  # "yam"
+Afrịka:Afrịka   # "africa"
+ọgwụ:ọgwụ    # "medicine"
+ikpe:ikpe   # "case"
+Septemba:Septemba  # "September"
+Jenụwarị:Jenụwarị   # "January"
+
+
+
 
 #================#
  LEXICON Pronouns
@@ -285,7 +314,8 @@ m:m      # "I, me"
 gị:gị     # "you"
 ọ:ọ     # "she, he"
 ya:ya     # "it"
-anyị:anyị     # "we, us"
+anyị:anyị     # "we"
+anyi:anyi  # "us"
 ihe:ihe     # "somthing"
 ụfọdụ:ụfọdụ     # "some"
 ha-abụọ:ha-abụọ     # "both"
@@ -295,6 +325,7 @@ nkaa:nkaa     # "that"
 ihe-obula:ihe-obula     # "everything, anything"
 
 
+
 #=============#
  LEXICON Verbs
 #=============#
@@ -302,73 +333,77 @@ ihe-obula:ihe-obula     # "everything, anything"
 iri:ri   # "eat"
 ibi:bi   # "live"
 iga:ga   # "walk"
-agaghari:agaghari   # "walks"
-ogige:ogige   # "garden"
-azịza:azịza     # "answer"
-ajụjụ:ajụjụ   # "question"
+na-aga:na-aga   # "walks"
+ịza:za     # "answer"
 nọ:nọ    # "is, are"
-chọta:chọta     # "find"
+ịchọta:chọta     # "find"
 #chọtara:chọtara   # "found"
 ga:ga   # "must"
 ibụ:bụ   # "be"
-idi:di   # "be"
-nwere:nwere   # "have, has"
-imẹ:mẹ   # "make"
+bụ:bụ 	# "am"
+dị:dị   # "is"
+inwe:nwe   # "have, has"
+ime:me   # "make"
 isi:si   # "say"
-kwuoo:kwuoo   # "says"
-ijẹ:jẹ   # "go"
+kwuo:kwuo   # "says"
+ije:je   # "go"
 #gara:gara   # "went"
 ima:ma   # "know"
 #maara:maara   # "knows"
-ifụ:fụ   # "see"
+ihụ:hụ   # "see"
 ibia:bia   # "come"
 ichẹ:chẹ   # "think"
 chee:chee   # "thinks"
-inẹ:nẹ   # "look"
-lee-anya:lee-anya     # "looks"
+ine:ne   # "look"
+nee-anya:nee-anya     # "looks"
 choo:choo   # "want"
-inyẹ:nyẹ   # "give"
+inye:nye   # "give"
 iji:ji   # "use"
 igwa:gwa   # "tell"
-ijụ:jụ   # "ask"
-ilu:lu   # "work"
-irapụ:rapụ   # "leave"
-ikpọ:kpọ   # "call"
-ichu:chu   # "chase"
+ịjụ:jụ   # "ask"
+iru:ru   # "work"
+ọrụ:ọrụ  # "task"
+ịhapụ:hapụ   # "leave"
+ịkpọ:kpọ   # "call"
+ịchu:chu   # "chase"
 ide:de   # "write"
-igafe:gafe   # "pass"
+ịgafe:gafe   # "pass"
 igba:gba   # "dance"
 igbachi:gbachi   # "lock"
 icheta:cheta   # "remember"
-ikagbu:kagbu   # "cancel"
-inodu:nodu   # "sit"
+ịkagbu:kagbu   # "cancel"
+ịnọdụ:nọdụ   # "sit"
 itu:tu   # "throw" 
-#eme:me   # "does, doing"
+#eme:me   # "does"
+na-eme:na-eme # "doing"
 ime:me   # "do"
 #mere:mere   # "did"
 inwa:nwa   # "try"
-iwo:wo   # "become"
+ibu:bu   # "become"
 ibido:bido   # "begin"
-ezigbo:ezigbo    # "very"
-ụda:ụda   # "sound"
-nwere-ike:nwere-ike     # "can"
+nwere\ ike:nwere\ ike     # "can"
 oge:oge     # "time"
-ṅụọ:ṅụọ     # "drink"
-achị-ọchị:achị-ọchị     # "laughs"
-inu:inu     # "hear"
-gee-nti:gee-nti     # "listens, listen"
-zaghachi:zaghachi     # "replies"
-hụrụ:hụrụ     # "seen"
-igwu-egwu:igwu-egwu     # "play"
-gbaaoso:gbaaoso     # "runs"
+ịnụọ:nụọ     # "drink"
+achị\ ọchị:achị\ ọchị     # "laughs"
+ịnụ:nụ     # "hear"
+ịge\ ntị:ge\ ntị     # "listens, listen"
+ịzaghachi:zaghachi     # "replies"
+ịhụrụ:hụrụ     # "seen"
+igwu\ egwu:gwu\ egwu     # "play"
+igba\ oso:gba\ oso     # "runs"
 ezo:ezo     # "hiding"
-kwuo:kwuo     # "speak"
-nweta:nweta     # "get, gets"
+ikwu\ okwu:kwu\ okwu     # "speak"
+inweta:nweta     # "get, gets"
 enweghị-ike:enweghị-ike     # "can't, cannot"
 ọdụ:ọdụ   # "sitting"
-ọnọ-ọgụgụ:ọnọ-ọgụgụ     # "counting"
-ihu-n'anya:ihu-n'anya     # "love"
+ọnọ\ ọgụgụ:ọnọ\ ọgụgụ     # "counting"
+ịhụnanya:hụnanya    # "love"
 mmasị:mmasị     # "likes"
+iche:iche  # "assume"
+bụrụ:bụrụ  	# "take"
+nyere:nyere  # "given"
+malitere:malitere  # "started"
+bidoro:bidoro # "start"
 
 
 #=================#
@@ -407,13 +442,13 @@ oyi:oyi	# "cold"
 ọhụrụ:ọhụrụ	# "new"
 agadị:agadị	# "old"
 ochie:ochie	# "old"
-
+Steeti:Steeti  # "state"
 nke-ahụ:nke-ahụ # "that"
-ndi-ahụ:ndi-ahụ # "those"
+ndị:ndị   # "those"
 nke-a:nke-a	# "this"
 ndị-a:ndỊ-a	# "these"
-
-
+mụrụ:mụrụ      # "born"
+ọtụtụ:ọtụtụ   # "many"
 öjöö:öjöö    # "ugly, "
 obele:obele    # "small"
 niile:niile    # "all, each, every"
@@ -426,6 +461,8 @@ nyocha:nyocha    # "searching"
 na-anwa:na-anwa    # "trying"
 abia:abia     # "coming"
 nke-ha:nke-ha     # "theirs"
+igbo:igbo   # "ibo"
+mpaghara:mpaghara  # "local"
 
 ojii:ojii	# "black"
 igwe-igwe:igwe-igwe # "blue"
@@ -446,7 +483,7 @@ edo-edo:edo-edo   # "yellow"
  LEXICON Prepositions
 #===================#
 
-maka:maka	# "about, for, of"
+maka:maka	# "for, of"
 n'elu:n'elu	# "above"
 gburugburu:gburugburu # "around"
 n'akụkụ:n'akụkụ # "aside, beside"
@@ -472,10 +509,13 @@ kemgbe:kemgbe	# "since"
 ya-mere:ya-mere # "therefore"
 site-na:site-na # "through" 
 n'okpuru:n'okpuru # "under"
-ruo-mgbe:ruo-mgbe # "until"
-
+ruo\ mgbe:ruo\ mgbe # "until"
+dị\ ka:dị\ ka  # "such as"
+dika:dika 	# "according"
 na:na      # "in, with"
-
+gụnyere:gụnyere  # "including"
+nakwa:nakwa   # "as well"
+banyere:banyere   # "about"
 
 #=================#
  LEXICON Adverbs
@@ -484,6 +524,7 @@ na:na      # "in, with"
 Ebee:Ebee   # "where"
 agaghị:agaghị   # "never"
 mba:mba   # "no"
+ezigbo:ezigbo    # "very"
 n'ihu:n'ihu    # "front"
 afọ:afọ   # "years"
 nso:nso   # "near"
@@ -509,7 +550,8 @@ mgbe-niile:mgbe-niile     # "always"
 ọnụ:ọnụ     # "together"
 ya-mere:ya-mere     # "so"
 maka-gini:maka-gini     # "why"
-
+ma:ma   # "yet"
+mbụ:mbụ   # "first"
 
 
 #=================#
@@ -537,8 +579,8 @@ a:a     # "a"
 
 otu:otu   # "1"
 abụọ:abụọ   # "2"
-atö:atö   # "3"
-anö:anö   # "4"
+atọ:atọ   # "3"
+anọ:anọ   # "4"
 ise:ise   # "5, five"
 isii:isii   # "6, six"
 asaa:asaa   # "7"
diff --git a/texts/wikipedia_corpus.txt b/texts/wikipedia_corpus.txt
new file mode 100644
index 0000000..ff69b27
--- /dev/null
+++ b/texts/wikipedia_corpus.txt
@@ -0,0 +1,100 @@
+TOP 100 UNKNOWN WORDS:
+bụ:bụ
+ndị:ndị
+dị:dị
+ọrụ:ọrụ
+ma:ma
+bu:bu
+ndi:ndi
+egwu:egwu
+of:of
+ebe:ebe
+nkiri:nkiri
+o:o
+iche:iche
+ubochi:ubochi
+O:O
+Nigeria:Nigeria
+Naijiria:Naijiria
+n'afọ:n'afọ
+dịka:dịka
+Naịjirịa:Naịjirịa 
+the:the
+mbụ:mbụ
+ụmụ:ụmụ
+mmadụ:mmadụ
+mere:mere
+Mahadum:Mahadum
+and:and
+nwanyị:nwanyị
+e:e
+atọ:atọ
+Ọrụ:Ọrụ
+ọtụtụ:ọtụtụ
+State:State
+oge:oge
+ga:ga
+ana-kpo:ana-kpo
+dika:dika
+Igbo:Igbo
+akụkọ:akụkọ
+ana:ana
+aha:aha
+mụrụ:mụrụ
+Lagos:Lagos
+Africa:Africa
+bụrụ:bụrụ
+Steeti:Steeti
+ndọrọ:ndọrọ
+s:s
+nọ:nọ
+kpo:kpo
+agha:agha
+no:no
+The:The
+ọchịchị:ọchịchị
+wee:wee
+anọ:anọ
+in:in
+ego:ego
+ruo:ruo
+ozi:ozi
+ọrịa:ọrịa
+Ndị:Ndị
+ọnwa:ọnwa
+iwu:iwu
+onwe:onwe
+year:year
+Gregorian:Gregorian
+gụnyere:gụnyere
+nà:nà
+du:du
+leap:leap
+agwu:agwu
+mpaghara:mpaghara
+nwere agugu:nwere agugu
+calender:calender
+akpọrọ:akpọrọ
+okwu:okwu
+Anyi:Anyi
+to:to
+kwa:kwa
+amụrụ:amụrụ
+nyere:nyere
+nna:nna
+ji:ji
+nakwa:nakwa
+banyere:banyere
+malitere:malitere
+United:United
+Afrịka:Afrịka
+ọgwụ:ọgwụ
+ikpe:ikpe
+nwere ike:nwere ike
+Mee:Mee
+University:University
+bidoro:bidoro
+Septemba:Septemba
+Jenụwarị:Jenụwarị
+akpọ:akpọ
+n'ọnwa:n'ọnwa