[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » user » zeman » treebanks » te

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
user:zeman:treebanks:te [2012/03/22 16:47]
zeman ICON 2010 Telugu data size. 		user:zeman:treebanks:te [2012/03/22 18:18]
zeman Parsing.
Line 61: Line 61:
 ==== Inside ==== ==== Inside ====
  
-The text uses the [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/map.pdf|WX encoding]] of Indian letters. If we know what the original script is (Bengali in this case) we can map the WX encoding to the original characters in UTF-8. WX uses English letters so if there was embedded English (or other string using Latin letters) it will probably get lost during the conversion.+The text uses the [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/map.pdf|WX encoding]] of Indian letters. If we know what the original script is (Telugu in this case) we can map the WX encoding to the original characters in UTF-8. WX uses English letters so if there was embedded English (or other string using Latin letters) it will probably get lost during the conversion.
  
 The CoNLL format contains only the chunk heads. The native SSF format shows the other words in the chunk, too, but it does not capture intra-chunk dependency relations. This is an example of a multi-word chunk: The CoNLL format contains only the chunk heads. The native SSF format shows the other words in the chunk, too, but it does not capture intra-chunk dependency relations. This is an example of a multi-word chunk:
  
-<code>3       ((      NP      <fs af='rumAla,n,,sg,,d,0,0' head="rumAla" drel=k2:VGF name=NP3> +<code>3       ((      NP      <fs af='AdavAlYlu,n,,sg,,,0,0_e' head='AdavAlYle' pbank='ARG3' name='NP3'> 
-3.1     ekatA   QC      <fs af='eka,num,,,,,,'> +3.1     932     QC      <fs af='932,num,,,,,,'> 
-3.2     ledisa  JJ      <fs af='ledisa,unk,,,,,,'> +3.2     maMxi   CL      <fs af='maMxi,n,,pl,,d,0,0'> 
-3.3     rumAla  NN      <fs af='rumAla,n,,sg,,d,0,0' name="rumAla">+3.3     AdavAlYle       NN      <fs af='AdavAlYlu,n,,sg,,,0,0_e' name='AdavAlYle'>
         ))</code>         ))</code>
  
Line 79: Line 79:
 According to [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/toolscontest10-workshoppaper-final.pdf|(Husain et al., 2010)]], in the ICON 2010 version, the chunk tags, POS tags and inter-chunk dependencies (topology + tags) were annotated manually. The rest (lemma, morphosyntactic features, headword of chunk) was marked automatically. According to [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/toolscontest10-workshoppaper-final.pdf|(Husain et al., 2010)]], in the ICON 2010 version, the chunk tags, POS tags and inter-chunk dependencies (topology + tags) were annotated manually. The rest (lemma, morphosyntactic features, headword of chunk) was marked automatically.
  
-Note: There have been cycles in the Hindi part of HyDT but no such problem occurs in the Bengali part.+Note: There have been cycles in the Hindi part of HyDT but no such problem occurs in the Telugu part.
  
 ==== Sample ==== ==== Sample ====
Line 85: Line 85:
 The first sentence of the ICON 2010 training data (with fine-grained syntactic tags) in the Shakti format: The first sentence of the ICON 2010 training data (with fine-grained syntactic tags) in the Shakti format:
  
-<code xml><document id=""> +<code xml><document id="">
 <head> <head>
-<annotated-resource name="HyDT-Bangla" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="ben" date-of-release="20100831">+<annotated-resource name="HyDT-Telugu" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="tel" date-of-release="20100831">
     <annotation-standard>     <annotation-standard>
         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />
Line 94: Line 94:
         <dependency-standard name="Anncorra-dep" version="2.0" date="" dep-tagset-granularity="6" />         <dependency-standard name="Anncorra-dep" version="2.0" date="" dep-tagset-granularity="6" />
     </annotation-standard>     </annotation-standard>
-</annotated-resource>  +</annotated-resource> 
-</head> +</head>
 <Sentence id="1"> <Sentence id="1">
-1 (( NP <fs af='Age,adv,,,,,,' head="Agei" drel=k7t:VGF name=NP> +1       ((      NP      <fs af='saMgawi,n,,sg,,d,0,0' head='saMgawi' drel='k1:VGF'> 
-1.1 mudZira NN <fs af='mudZi,n,,sg,,o,era,era'> +1.1     maro    QF      <fs af='maro,avy,,,,,,'> 
-1.2 Agei NST <fs af='Age,adv,,,,,,' name="Agei"> +1.2     saMgawi NN      <fs af='saMgawi,n,,sg,,d,0,0' name='saMgawi'> 
- ))  +        )) 
-2 (( NP <fs af='cA,n,,sg,,d,0,0' head="cA" drel=k1:VGF name=NP2> +2       ((      NP      <fs af='mIru,pn,any,pl,2,,ki,ki' head='mIku' drel='k4:VGF' name='NP2'> 
-2.1 praWama QO <fs af='praWama,num,,,,,,'> +2.1     mIku    PRP     <fs af='mIru,pn,any,pl,2,,ki,ki' name='mIku'> 
-2.2 kApa NN <fs af='kApa,unk,,,,,,'> +        )) 
-2.3 cA NN <fs af='cA,n,,sg,,d,0,0' name="cA"> +3       ((      VGF     <fs af='weVlusA,avy,,,,,0,0_avy' head='weVlusA' name='VGF'> 
- ))  +3.1     weVlusA VM      <fs af='weVlusA,avy,,,,,0,0_avy' name='weVlusA'> 
-3 (( VGF <fs af='As,v,,,5,,A_yA+Ce,A' head="ese" name=VGF> +3.2     ?       SYM     <fs af='?,punc,,,,,,'> 
-3.1 ese VM <fs af='As,v,,,7,,A,A' name="ese"> +        ))
-3.2 . SYM <fs af='.,punc,,,,,,'> +
- )) +
 </Sentence></code> </Sentence></code>
  
 And in the CoNLL format: And in the CoNLL format:
  
-| 1 | Agei | Age | NP | NST | lex-Age<nowiki>|</nowiki>cat-adv<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-Agei<nowiki>|</nowiki>name-NP | 3 | k7t | _ | _ | +| 1 | saMgawi | saMgawi | NP | NN | <nowiki>lex-saMgawi|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-saMgawi</nowiki> | 3 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | cA | cA | NP | NN | lex-cA<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-cA<nowiki>|</nowiki>name-NP2 | 3 | k1 | _ | _ | +| 2 | mIku | mIru | NP | PRP | <nowiki>lex-mIru|cat-pn|gend-any|num-pl|pers-2|case-|vib-ki|tam-ki|head-mIku|name-NP2</nowiki> | 3 | k4 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | ese | As | VGF | VM | lex-As<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-A_yA+Ce<nowiki>|</nowiki>tam-A<nowiki>|</nowiki>head-ese<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+| 3 | weVlusA | weVlusA | VGF | VM | <nowiki>lex-weVlusA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-weVlusA|name-VGF</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
  
-And after conversion of the WX encoding to the Bengali script in UTF-8:+And after conversion of the WX encoding to the Telugu script in UTF-8:
  
-| 1 | আগেই | আগে | NP | NST | lex-Age<nowiki>|</nowiki>cat-adv<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-Agei<nowiki>|</nowiki>name-NP | 3 | k7t | _ | _ | +| 1 | <nowiki>సంగతి</nowiki> | <nowiki>సంగతి</nowiki> | NP | NN | <nowiki>lex-saMgawi|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-saMgawi</nowiki> | 3 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | চা | চা | NP | NN | lex-cA<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-cA<nowiki>|</nowiki>name-NP2 | 3 | k1 | _ | _ | +| 2 | <nowiki>మీకు</nowiki> | <nowiki>మీరు</nowiki> | NP | PRP | <nowiki>lex-mIru|cat-pn|gend-any|num-pl|pers-2|case-|vib-ki|tam-ki|head-mIku|name-NP2</nowiki> | 3 | k4 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | এসে | আস্ | VGF | VM | lex-As<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-A_yA+Ce<nowiki>|</nowiki>tam-A<nowiki>|</nowiki>head-ese<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+| 3 | <nowiki>తెలుసా</nowiki> | <nowiki>తెలుసా</nowiki> | VGF | VM | <nowiki>lex-weVlusA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-weVlusA|name-VGF</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
  
 The first sentence of the ICON 2010 development data (with fine-grained syntactic tags) in the Shakti format: The first sentence of the ICON 2010 development data (with fine-grained syntactic tags) in the Shakti format:
Line 128: Line 126:
 <code xml><document id=""> <code xml><document id="">
 <head> <head>
-<annotated-resource name="HyDT-Bangla" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="ben" date-of-release="20100831">+<annotated-resource name="HyDT-Telugu" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="tel" date-of-release="20100831">
     <annotation-standard>     <annotation-standard>
         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />
Line 138: Line 136:
 </head> </head>
 <Sentence id="1"> <Sentence id="1">
-1 (( NP <fs af='parabarwIkAle,adv,,,,,,' head="parabarwIkAle" drel=k7t:VGF name=NP> +1       ((      RBP     <fs af='eVMwa,pn,,sg,,d,0,0' head='eVMwa' drel='adv:NP'> 
-1.1 parabarwIkAle NN <fs af='parabarwIkAle,adv,,,,,,' name="parabarwIkAle"> +1.1     eVMwa   WQ      <fs af='eVMwa,pn,,sg,,d,0,0' name='eVMwa'> 
- ))  +        )) 
-2 (( NP <fs af='aPisa-biyArAraxera,unk,,,,,,' head="aPisa-biyArAraxera" drel=r6:NP3 name=NP2> +2       ((      NP      <fs af='bAXEnA,unk,,,,,,' head='bAXEnA' drel='k2s:VGNF' name='NP'> 
-2.1 aPisa-biyArAraxera NN <fs af='aPisa-biyArAraxera,unk,,,,,,' name="aPisa-biyArAraxera"> +2.1     bAXEnA  NN      <fs af='bAXEnA,unk,,,,,,' name='bAXEnA'> 
- ))  +        )) 
-3 (( NP <fs af='nAma,n,,sg,,d,0,0' head="nAma" drel=k2:VGNN name=NP3> +3       ((      NP      <fs af='ixi,pn,fn,sg,3,o,ti,ti' head='xIni' drel='k2:VGNF' name='NP2'> 
-3.1 nAma NN <fs af='nAma,n,,sg,,d,0,0' name="nAma"> +3.1     xIni    PRP     <fs af='ixi,pn,fn,sg,3,o,ti,ti' name='xIni'> 
- ))  +        )) 
-4 (( NP <fs af='GoRaNA,unk,,,,,,' head="GoRaNA" drel=pof:VGNN name=NP4> +4       ((      RBP     <fs af='eVlA,avy,,,,,0,0_avy' head='eVlA' drel='adv:VGNF' name='RBP2'> 
-4.1 GoRaNA NN <fs af='GoRaNA,unk,,,,,,' name="GoRaNA"> +4.1     eVlA    WQ      <fs af='eVlA,avy,,,,,0,0_avy' name='eVlA'> 
- ))  +        )) 
-5 (( VGNN <fs af='kar,n,,,any,,,' head="karAra" drel=r6:NP5 name=VGNN> +5       ((      NP      <fs af='bayata,n,,sg,,d,0,0' head='bayata' drel='pof:VGNF' name='NP3'> 
-5.1 karAra VM <fs af='kar,n,,,any,,,' name="karAra"> +5.1     bayata  NST     <fs af='bayata,n,,sg,,d,0,0' name='bayata'> 
- ))  +        )) 
-6 (( NP <fs af='samay,unk,,,,,,' head="samay" drel=k7t:VGF name=NP5> +6       ((      VGNF    <fs af='peVttuko,pn,,sg,,,e_axi,e_axi_0' head='peVttukoVnexi' drel='k1s:VGNN' name='VGNF'> 
-6.1 samay NN <fs af='samay,unk,,,,,,' name="samay"> +6.1     peVttukoVnexi   VM      <fs af='peVttuko,pn,,sg,,,e_axi,e_axi_0' name='peVttukoVnexi'> 
- ))  +        )) 
-7 (( NP <fs af='animeRake,unk,,,,,,' head="animeRake" drel=k2:VGF name=NP6> +7       ((      RBP     <fs af='sarigA,avy,,,,,0,0_avy' head='sarigA' drel='adv:VGNN' name='RBP3'> 
-7.1 animeRake NNP <fs af='animeRake,unk,,,,,,' name="animeRake"> +7.1     sarigA  RB      <fs af='sarigA,avy,,,,,0,0_avy' name='sarigA'> 
- ))  +        )) 
-8 (( VGF <fs af='sariye,unk,,,5,,0_rAKA+ka_ha+la,' head="sariye" name=VGF> +8       ((      NP      <fs af='viRayaM,n,,sg,,d,0,0' head='viRayaM' drel='k1:VGNN' name='NP4'> 
-8.1 sariye VM <fs af='sariye,unk,,,,,,' name="sariye"> +8.1     viRayaM NN      <fs af='viRayaM,n,,sg,,d,0,0' name='viRayaM'> 
-8.2 . SYM <fs af='.,punc,,,,,,'> +        )) 
- )) +9       ((      VGNN    <fs af='weVliyu,v,any,any,any,,aka_po_adaM,aka_po_adaM' head='weVliyakapovadaM' name='VGNN'> 
 +9.1     weVliyakapovadaM        VM      <fs af='weVliyu,v,any,any,any,,aka_po_adaM,aka_po_adaM' name='weVliyakapovadaM'> 
 +9.2     .       SYM     <fs af='.,punc,,,,,,'> 
 +        ))
 </Sentence></code> </Sentence></code>
  
 And in the CoNLL format: And in the CoNLL format:
  
-| 1 | parabarwIkAle | parabarwIkAle | NP | NN | lex-parabarwIkAle<nowiki>|</nowiki>cat-adv<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-parabarwIkAle<nowiki>|</nowiki>name-NP | 8 | k7t | _ | _ | +| 1 | eVMwa | eVMwa | RBP | WQ | <nowiki>lex-eVMwa|cat-pn|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-eVMwa</nowiki> | 2 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | aPisa-biyArAraxera | aPisa-biyArAraxera | NP | NN | lex-aPisa-biyArAraxera<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-aPisa-biyArAraxera<nowiki>|</nowiki>name-NP2 | 3 | r6 | _ | _ | +| 2 | bAXEnA | bAXEnA | NP | NN | <nowiki>lex-bAXEnA|cat-unk|gend-|num-|pers-|case-|vib-|tam-|head-bAXEnA|name-NP</nowiki> | 6 | k2s | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | nAma | nAma | NP | NN | lex-nAma<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-nAma<nowiki>|</nowiki>name-NP3 | 5 | k2 | _ | _ | +| 3 | xIni | ixi | NP | PRP | <nowiki>lex-ixi|cat-pn|gend-fn|num-sg|pers-3|case-o|vib-ti|tam-ti|head-xIni|name-NP2</nowiki> | 6 | k2 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 4 | GoRaNA | GoRaNA | NP | NN | lex-GoRaNA<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-GoRaNA<nowiki>|</nowiki>name-NP4 | 5 | pof | _ | _ | +| 4 | eVlA | eVlA | RBP | WQ | <nowiki>lex-eVlA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-eVlA|name-RBP2</nowiki> | 6 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 5 | karAra | kar | VGNN | VM | lex-kar<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-any<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-karAra<nowiki>|</nowiki>name-VGNN | 6 | r6 | _ | _ | +| 5 | bayata | bayata | NP | NST | <nowiki>lex-bayata|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-bayata|name-NP3</nowiki> | 6 | pof | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 6 | samay | samay | NP | NN | lex-samay<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-samay<nowiki>|</nowiki>name-NP5 | 8 | k7t | _ | _ | +| 6 | peVttukoVnexi | peVttuko | VGNF | VM | <nowiki>lex-peVttuko|cat-pn|gend-|num-sg|pers-|case-|vib-e_axi|tam-e_axi_0|head-peVttukoVnexi|name-VGNF</nowiki> | 9 | k1s | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 7 | animeRake | animeRake | NP | NNP | lex-animeRake<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-animeRake<nowiki>|</nowiki>name-NP6 | 8 | k2 | _ | _ | +| 7 | sarigA | sarigA | RBP | RB | <nowiki>lex-sarigA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-sarigA|name-RBP3</nowiki> | 9 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 8 | sariye | sariye | VGF | VM | lex-sariye<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-0_rAKA+ka_ha+la<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-sariye<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+| 8 | viRayaM | viRayaM | NP | NN | <nowiki>lex-viRayaM|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-viRayaM|name-NP4</nowiki> | 9 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
 +| 9 | weVliyakapovadaM | weVliyu | VGNN | VM | <nowiki>lex-weVliyu|cat-v|gend-any|num-any|pers-any|case-|vib-aka_po_adaM|tam-aka_po_adaM|head-weVliyakapovadaM|name-VGNN</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
  
-And after conversion of the WX encoding to the Bengali script in UTF-8:+And after conversion of the WX encoding to the Telugu script in UTF-8:
  
-| 1 | পরবর্তীকালে | পরবর্তীকালে | NP | NN | lex-parabarwIkAle<nowiki>|</nowiki>cat-adv<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-parabarwIkAle<nowiki>|</nowiki>name-NP | 8 | k7t | _ | _ | +| 1 | <nowiki>ఎంత</nowiki> | <nowiki>ఎంత</nowiki> | RBP | WQ | <nowiki>lex-eVMwa|cat-pn|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-eVMwa</nowiki> | 2 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | অফিস-বিযারারদের | অফিস-বিযারারদের | NP | NN | lex-aPisa-biyArAraxera<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-aPisa-biyArAraxera<nowiki>|</nowiki>name-NP2 | 3 | r6 | _ | _ | +| 2 | <nowiki>బాధైనా</nowiki> | <nowiki>బాధైనా</nowiki> | NP | NN | <nowiki>lex-bAXEnA|cat-unk|gend-|num-|pers-|case-|vib-|tam-|head-bAXEnA|name-NP</nowiki> | 6 | k2s | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | নাম | নাম | NP | NN | lex-nAma<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-nAma<nowiki>|</nowiki>name-NP3 | 5 | k2 | _ | _ | +| 3 | <nowiki>దీని</nowiki> | <nowiki>ఇది</nowiki> | NP | PRP | <nowiki>lex-ixi|cat-pn|gend-fn|num-sg|pers-3|case-o|vib-ti|tam-ti|head-xIni|name-NP2</nowiki> | 6 | k2 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 4 | ঘোষণা | ঘোষণা | NP | NN | lex-GoRaNA<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-GoRaNA<nowiki>|</nowiki>name-NP4 | 5 | pof | _ | _ | +| 4 | <nowiki>ఎలా</nowiki> | <nowiki>ఎలా</nowiki> | RBP | WQ | <nowiki>lex-eVlA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-eVlA|name-RBP2</nowiki> | 6 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 5 | করার | কর্ | VGNN | VM | lex-kar<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-any<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-karAra<nowiki>|</nowiki>name-VGNN | 6 | r6 | _ | _ | +| 5 | బయట | బయట | NP | NST | <nowiki>lex-bayata|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-bayata|name-NP3</nowiki> | 6 | pof | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 6 | সময্ | সময্ | NP | NN | lex-samay<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-samay<nowiki>|</nowiki>name-NP5 | 8 | k7t | _ | _ | +| 6 | <nowiki>పెట్టుకొనేది</nowiki> | <nowiki>పెట్టుకొ</nowiki> | VGNF | VM | <nowiki>lex-peVttuko|cat-pn|gend-|num-sg|pers-|case-|vib-e_axi|tam-e_axi_0|head-peVttukoVnexi|name-VGNF</nowiki> | 9 | k1s | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 7 | অনিমেষকে | অনিমেষকে | NP | NNP | lex-animeRake<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-animeRake<nowiki>|</nowiki>name-NP6 | 8 | k2 | _ | _ | +| 7 | <nowiki>సరిగా</nowiki> | <nowiki>సరిగా</nowiki> | RBP | RB | <nowiki>lex-sarigA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-sarigA|name-RBP3</nowiki> | 9 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 8 | সরিযে | সরিযে | VGF | VM | lex-sariye<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-0_rAKA+ka_ha+la<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-sariye<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+| 8 | <nowiki>విషయం</nowiki> | <nowiki>విషయం</nowiki> | NP | NN | <nowiki>lex-viRayaM|cat-n|gend-|num-sg|pers-|case-d|vib-0|tam-0|head-viRayaM|name-NP4</nowiki> | 9 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
 +| 9 | <nowiki>తెలియకపొవడం</nowiki> | <nowiki>తెలియు</nowiki> | VGNN | VM | <nowiki>lex-weVliyu|cat-v|gend-any|num-any|pers-any|case-|vib-aka_po_adaM|tam-aka_po_adaM|head-weVliyakapovadaM|name-VGNN</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
  
 The first sentence of the ICON 2010 test data (with fine-grained syntactic tags) in the Shakti format: The first sentence of the ICON 2010 test data (with fine-grained syntactic tags) in the Shakti format:
Line 191: Line 194:
 <code xml><document id=""> <code xml><document id="">
 <head> <head>
-<annotated-resource name="HyDT-Bangla" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="ben" date-of-release="20101013">+<annotated-resource name="HyDT-Telugu" version="0.5" type="dep-interchunk-only" layers="morph,pos,chunk,dep-interchunk-only" language="tel" date-of-release="20101013">
     <annotation-standard>     <annotation-standard>
         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />         <morph-standard name="Anncorra-morph" version="1.31" date="20080920" />
- <pos-standard name="Anncorra-pos" version="" date="20061215" /> +        <pos-standard name="Anncorra-pos" version="" date="20061215" /> 
- <chunk-standard name="Anncorra-chunk" version="" date="20061215" /> +        <chunk-standard name="Anncorra-chunk" version="" date="20061215" /> 
- <dependency-standard name="Anncorra-dep" version="2.0" date="" dep-tagset-granularity="6" />+        <dependency-standard name="Anncorra-dep" version="2.0" date="" dep-tagset-granularity="6" />
     </annotation-standard>     </annotation-standard>
-<annotated-resource>+</annotated-resource>
 </head> </head>
-<Sentence id="1"> +<Sentence id="29"> 
-1 (( NP <fs af='mAXabIlawA,n,,sg,,d,0,0' head="mAXabIlawA" drel=k1:VGF name=NP> +1       ((      NP      <fs af='iMkA,avy,,,,,0,0_avy' head="iMkA" drel=vmod:NULL_VGF name=NP poslcat="NM"> 
-1.1 mAXabIlawA NNP <fs af='mAXabIlawA,n,,sg,,d,0,0' name="mAXabIlawA"> +1.1     iMkA    PRP     <fs af='iMkA,avy,,,,,0,0_avy' poslcat="NM" name="iMkA"> 
- ))  +        )) 
-2 (( NP <fs af='waKana,pn,,,,d,0,0' head="waKana" drel=k7t:VGF name=NP2> +2       ((      RBP     <fs af='warawarAlugA,avy,,,,,0,0_avy' head="warawarAlugA" drel=adv:VGNF name=RBP poslcat="NM"> 
-2.1 waKana PRP <fs af='waKana,pn,,,,d,0,0' name="waKana"> +2.1     warawarAlugA    RB      <fs af='warawarAlugA,avy,,,,,0,0_avy' poslcat="NM" name="warawarAlugA"> 
- ))  +        )) 
-3 (( NP <fs af='hAwa,n,,sg,,o,era,era' head="hAwera" drel=r6:NP4 name=NP3> +3       ((      VGNF    <fs af='nAtuko,v,any,any,any,,i_po_ina,i_po_ina' head="nAtukupoyina" drel=nmod:NP2 name=VGNF> 
-3.1 hAwera NN <fs af='hAwa,n,,sg,,o,era,era' name="hAwera"> +3.1     nAtukupoyina    VM      <fs af='nAtuko,v,any,any,any,,i_po_ina,i_po_ina' name="nAtukupoyina"> 
- ))  +        )) 
-4 (( NP <fs af='GadZi,unk,,,,,,' head="GadZi" drel=k2:VGNF name=NP4> +4       ((      NP      <fs af='aBiprAyaM,n,,pl,,d,0,0' head="aBiprAyAlu" drel=k1:NULL_VGF name=NP2> 
-4.1 GadZi NN <fs af='GadZi,unk,,,,,,' name="GadZi"> +4.1     aBiprAyAlu      NN      <fs af='aBiprAyaM,n,,pl,,d,0,0' name="aBiprAyAlu"> 
- ))  +        )) 
-5 (( VGNF <fs af='Kul,v,,,5,,ne,ne' head="Kule" drel=vmod:VGF name=VGNF> +5       ((      NULL_VGF        <fs name='NULL_VGF'> 
-5.1 Kule VM <fs af='Kul,v,,,5,,ne,ne' name="Kule"> +5.1     NULL    VM      <fs af='NULL,unk,,,,,,' poslcat="NM"> 
- ))  +5.2     .       SYM     <fs af='.,punc,,,,,,' poslcat="NM"> 
-6 (( NP <fs af='tebila,n,,sg,,d,me,me' head="tebile" drel=k7p:VGF name=NP5> +        ))
-6.1 tebile NN <fs af='tebila,n,,sg,,d,me,me' name="tebile"> +
- ))  +
-7 (( VGF <fs af='rAK,v,,,5,,Cila,Cila' head="rAKaCila" name=VGF> +
-7.1 rAKaCila VM <fs af='rAK,v,,,5,,Cila,Cila' name="rAKaCila"> +
-7.2 । SYM  +
- )) +
 </Sentence></code> </Sentence></code>
  
 And in the CoNLL format: And in the CoNLL format:
  
-| 1 | mAXabIlawA | mAXabIlawA | NP | NNP | lex-mAXabIlawA<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-mAXabIlawA<nowiki>|</nowiki>name-NP | 7 | k1 | _ | _ | +| 1 | iMkA | iMkA | NP | PRP | <nowiki>lex-iMkA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-iMkA|name-NP|poslcat-NM</nowiki> | 5 | vmod | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | waKana | waKana | NP | PRP | lex-waKana<nowiki>|</nowiki>cat-pn<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-waKana<nowiki>|</nowiki>name-NP2 | 7 | k7t | _ | _ | +| 2 | warawarAlugA | warawarAlugA | RBP | RB | <nowiki>lex-warawarAlugA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-warawarAlugA|name-RBP|poslcat-NM</nowiki> | 3 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | hAwera | hAwa | NP | NN | lex-hAwa<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-o<nowiki>|</nowiki>vib-era<nowiki>|</nowiki>tam-era<nowiki>|</nowiki>head-hAwera<nowiki>|</nowiki>name-NP3 | 4 | r6 | _ | _ | +| 3 | nAtukupoyina | nAtuko | VGNF | VM | <nowiki>lex-nAtuko|cat-v|gend-any|num-any|pers-any|case-|vib-i_po_ina|tam-i_po_ina|head-nAtukupoyina|name-VGNF</nowiki> | 4 | nmod | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 4 | GadZi | GadZi | NP | NN | lex-GadZi<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-GadZi<nowiki>|</nowiki>name-NP4 | 5 | k2 | _ | _ | +| 4 | aBiprAyAlu | aBiprAyaM | NP | NN | <nowiki>lex-aBiprAyaM|cat-n|gend-|num-pl|pers-|case-d|vib-0|tam-0|head-aBiprAyAlu|name-NP2</nowiki> | 5 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 5 | Kule | Kul | VGNF | VM | lex-Kul<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-ne<nowiki>|</nowiki>tam-ne<nowiki>|</nowiki>head-Kule<nowiki>|</nowiki>name-VGNF | 7 | vmod | _ | _ | +| 5 | NULL | NULL | <nowiki>NULL_VGF</nowiki> | VM | <nowiki>name-NULL_VGF</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
-| 6 | tebile | tebila | NP | NN | lex-tebila<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-me<nowiki>|</nowiki>tam-me<nowiki>|</nowiki>head-tebile<nowiki>|</nowiki>name-NP5 | 7 | k7p | _ | _ | +
-| 7 | rAKaCila | rAK | VGF | VM | lex-rAK<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-Cila<nowiki>|</nowiki>tam-Cila<nowiki>|</nowiki>head-rAKaCila<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+
  
-And after conversion of the WX encoding to the Bengali script in UTF-8:+And after conversion of the WX encoding to the Telugu script in UTF-8:
  
-| 1 | মাধবীলতা | মাধবীলতা | NP | NNP | lex-mAXabIlawA<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-mAXabIlawA<nowiki>|</nowiki>name-NP | 7 | k1 | _ | _ | +| 1 | <nowiki>ఇంకా</nowiki> | <nowiki>ఇంకా</nowiki> | NP | PRP | <nowiki>lex-iMkA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-iMkA|name-NP|poslcat-NM</nowiki> | 5 | vmod | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 2 | তখন | তখন | NP | PRP | lex-waKana<nowiki>|</nowiki>cat-pn<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-0<nowiki>|</nowiki>tam-0<nowiki>|</nowiki>head-waKana<nowiki>|</nowiki>name-NP2 | 7 | k7t | _ | _ | +| 2 | <nowiki>తరతరాలుగా</nowiki> | <nowiki>తరతరాలుగా</nowiki> | RBP | RB | <nowiki>lex-warawarAlugA|cat-avy|gend-|num-|pers-|case-|vib-0|tam-0_avy|head-warawarAlugA|name-RBP|poslcat-NM</nowiki> | 3 | adv | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 3 | হাতের | হাত | NP | NN | lex-hAwa<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-o<nowiki>|</nowiki>vib-era<nowiki>|</nowiki>tam-era<nowiki>|</nowiki>head-hAwera<nowiki>|</nowiki>name-NP3 | 4 | r6 | _ | _ | +| 3 | <nowiki>నాటుకుపొయిన</nowiki> | <nowiki>నాటుకొ</nowiki> | VGNF | VM | <nowiki>lex-nAtuko|cat-v|gend-any|num-any|pers-any|case-|vib-i_po_ina|tam-i_po_ina|head-nAtukupoyina|name-VGNF</nowiki> | 4 | nmod | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 4 | ঘড়ি | ঘড়ি | NP | NN | lex-GadZi<nowiki>|</nowiki>cat-unk<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-<nowiki>|</nowiki>tam-<nowiki>|</nowiki>head-GadZi<nowiki>|</nowiki>name-NP4 | 5 | k2 | _ | _ | +| 4 | <nowiki>అభిప్రాయాలు</nowiki> | <nowiki>అభిప్రాయం</nowiki> | NP | NN | <nowiki>lex-aBiprAyaM|cat-n|gend-|num-pl|pers-|case-d|vib-0|tam-0|head-aBiprAyAlu|name-NP2</nowiki> | 5 | k1 | <nowiki>_</nowiki> | <nowiki>_</nowiki> | 
-| 5 | খুলে | খুল্ | VGNF | VM | lex-Kul<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-ne<nowiki>|</nowiki>tam-ne<nowiki>|</nowiki>head-Kule<nowiki>|</nowiki>name-VGNF | 7 | vmod | _ | _ | +| 5 | NULL | NULL | <nowiki>NULL_VGF</nowiki> | VM | <nowiki>name-NULL_VGF</nowiki> | 0 | main | <nowiki>_</nowiki> | <nowiki>_</nowiki> |
-| 6 | টেবিলে | টেবিল | NP | NN | lex-tebila<nowiki>|</nowiki>cat-n<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-sg<nowiki>|</nowiki>pers-<nowiki>|</nowiki>case-d<nowiki>|</nowiki>vib-me<nowiki>|</nowiki>tam-me<nowiki>|</nowiki>head-tebile<nowiki>|</nowiki>name-NP5 | 7 | k7p | _ | _ | +
-| 7 | রাখছিল | রাখ্ | VGF | VM | lex-rAK<nowiki>|</nowiki>cat-v<nowiki>|</nowiki>gend-<nowiki>|</nowiki>num-<nowiki>|</nowiki>pers-5<nowiki>|</nowiki>case-<nowiki>|</nowiki>vib-Cila<nowiki>|</nowiki>tam-Cila<nowiki>|</nowiki>head-rAKaCila<nowiki>|</nowiki>name-VGF | 0 | main | _ | _ |+
  
 ==== Parsing ==== ==== Parsing ====
  
-Nonprojectivities in HyDT-Bangla are not frequent. Only 78 of the 7252 chunks in the training+development ICON 2010 version are attached nonprojectively (1.08%).+Nonprojectivities in HyDT-Telugu are very rare. Only 13 of the 5722 chunks in the training+development ICON 2010 version are attached nonprojectively (0.23%).
  
-The results of the ICON 2009 NLP tools contest have been published in [[http://ltrc.iiit.ac.in/nlptools2009/CR/intro-husain.pdf|(Husain, 2009)]]. There were two evaluation rounds, the first with the coarse-grained syntactic tags, the second with the fine-grained syntactic tags. To reward language independence, only systems that parsed all three languages were officially ranked. The following table presents the Bengali/coarse-grained results of the four officially ranked systems, and the best Bengali-only* system.+The results of the ICON 2009 NLP tools contest have been published in [[http://ltrc.iiit.ac.in/nlptools2009/CR/intro-husain.pdf|(Husain, 2009)]]. There were two evaluation rounds, the first with the coarse-grained syntactic tags, the second with the fine-grained syntactic tags. To reward language independence, only systems that parsed all three languages were officially ranked. The following table presents the Telugu/coarse-grained results of the four officially ranked systems.
  
 ^ Parser (Authors) ^ LAS ^ UAS ^ ^ Parser (Authors) ^ LAS ^ UAS ^
-| Kolkata (De et al.)* | 84.29 | 90.32 | +| Malt (Nivre) | 62.44 | 86.28 | 
-| Hyderabad (Ambati et al.) | 78.25 | 90.22 | +| Mannem | 65.01 | 85.76 | 
-| Malt (Nivre) | 76.07 | 88.97 | +| Hyderabad (Ambati et al.) | 65.01 | 85.25 | 
-| Malt+MST (Zeman) | 71.49 | 86.89 | +| Malt+MST (Zeman) | 56.43 | 81.30 |
-| Mannem | 70.34 | 83.56 |+
  
-The results of the ICON 2010 NLP tools contest have been published in [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/toolscontest10-workshoppaper-final.pdf|(Husain et al., 2010)]], page 6. These are the best results for Bengali with fine-grained syntactic tags:+The results of the ICON 2010 NLP tools contest have been published in [[http://ltrc.iiit.ac.in/nlptools2010/files/documents/toolscontest10-workshoppaper-final.pdf|(Husain et al., 2010)]], page 6. These are the best results for Telugu with fine-grained syntactic tags:
  
 ^ Parser (Authors) ^ LAS ^ UAS ^ ^ Parser (Authors) ^ LAS ^ UAS ^
-| Attardi et al. | 70.66 | 87.41 | +| Kosaraju et al. | 70.12 | 91.82 | 
-| Kosaraju et al. | 70.55 | 86.16 | +| Attardi et al. | 65.61 | 90.48 | 
-| Kolachina et al. | 70.14 | 87.10 |+| Kolachina et al. | 68.11 | 90.15 |
  

[ Back to the navigation ] [ Back to the content ]