Difference between revisions of "Bengali and English/Issues"
Jump to navigation
Jump to search
| Line 2: | Line 2: | ||
* Problem analyzing words with enclitic 'টি' - it can analyze "বিষয়" to "^বিষয়/বিষয়<n><nt><nn><sg><nom>/বিষয়<n><nt><nn><sg><obj>$" but can't analyze "বিষয়টি". Similarly can "বস্তু" but not "বস্তুটি" |
* Problem analyzing words with enclitic 'টি' - it can analyze "বিষয়" to "^বিষয়/বিষয়<n><nt><nn><sg><nom>/বিষয়<n><nt><nn><sg><obj>$" but can't analyze "বিষয়টি". Similarly can "বস্তু" but not "বস্তুটি" |
||
* Some words have entries in bn.dix, yet they are not being analyzed with "lt-proc -a bn-en.automorf.bin". |
* Some words have entries in bn.dix, yet they are not being analyzed with "lt-proc -a bn-en.automorf.bin". |
||
<e lm="সময়"><i>সময়</i><par n="গড়__n_mf" /></e> |
|||
<e lm="জাতীয়"><i>জাতীয়</i><par n="টক__adj" /></e> |
|||
still the output: |
|||
echo "সময়" | lt-proc -a bn-en.automorf.bin |
|||
^সময়/*সময়$ |
|||
echo "জাতীয়" | lt-proc -a bn-en.automorf.bin |
|||
^জাতীয়/*জাতীয়$ |
|||
to check all of the instances of this problem i ran this: |
to check all of the instances of this problem i ran this: |
||
cat apertium-bn-en.bn.dix | grep '<e lm' | sed 's/.*lm=\"//g' | sed 's/\".*//g' | lt-proc -a bn-en.automorf.bin | grep '*' |
cat apertium-bn-en.bn.dix | grep '<e lm' | sed 's/.*lm=\"//g' | sed 's/\".*//g' | lt-proc -a bn-en.automorf.bin | grep '*' |
||
and |
and the output is: |
||
<pre> |
<pre> |
||
^রেসলিং/*রেসলিং$ |
^রেসলিং/*রেসলিং$ |
||
| Line 31: | Line 24: | ||
^ওই/*ওই$ |
^ওই/*ওই$ |
||
</pre> |
</pre> |
||
where there is no "সময়" or "জাতীয়" ! And I have cheked the analysis: |
|||
^সময়/সময়<n><mf><nn><sg><nom>/সময়<n><mf><nn><sg><obj>$ |
|||
^জাতীয়/জাতীয়<adj><mf>$ |
|||
==Tagset== |
==Tagset== |
||
Revision as of 12:29, 27 June 2011
Morphological Analyzer
- Problem analyzing words with enclitic 'টি' - it can analyze "বিষয়" to "^বিষয়/বিষয়<n><nt><nn><sg><nom>/বিষয়<n><nt><nn><sg><obj>$" but can't analyze "বিষয়টি". Similarly can "বস্তু" but not "বস্তুটি"
- Some words have entries in bn.dix, yet they are not being analyzed with "lt-proc -a bn-en.automorf.bin".
to check all of the instances of this problem i ran this:
cat apertium-bn-en.bn.dix | grep '<e lm' | sed 's/.*lm=\"//g' | sed 's/\".*//g' | lt-proc -a bn-en.automorf.bin | grep '*'
and the output is:
^রেসলিং/*রেসলিং$ ^ইঞ্জিনিয়ারিং/*ইঞ্জিনিয়ারিং$ ^শুটিং/*শুটিং$ ^ভবিষ্যৎ/*ভবিষ্যৎ$ ^মোড়/*মোড়$ ^সাক্ষাৎ/*সাক্ষাৎ$ ^বোলিং/*বোলিং$ ^লং/*লং$ ^কোচিং/*কোচিং$ ^ব্যাংকিং/*ব্যাংকিং$ ^ব্যাটিং/*ব্যাটিং$ ^সম্প্রদায়/*সম্প্রদায়$ ^উচ্চবিদ্যালয়/*উচ্চবিদ্যালয়$ ^বিদ্যুৎ/*বিদ্যুৎ$ ^কি/*কি$ ^ওই/*ওই$
Tagset
- Confusion on animacy 'elite': what is the exact definition ? Is these correct examples of <el> - "ক্রেতা", "বিদ্রোহী", "সহকারী" ? And is these not <el> for sure - "মেয়র", "ম্যাজিস্ট্রেট", "উপাচার্য"
- Unmatched paradigm: "মামা", "চাচা" should be <m><hu> with the pardefs "ভাই__n_m" or "লোক__n_m" but neither of the two provides enough inflections for "মামার" or "চাচার"
- What is the exact difference between <mf><nn> and <nt><nn> ? What are the exclusive properties ?
- The word "মায়ের" probably has no matching pardef. the pardef "মা__n_f" has no inflections like "-য়ের"
