Difference between revisions of "Dhivehi/Transducer"

From LING073
Jump to: navigation, search
(→‎Final Evaluation of Morphological Generation)
 
(43 intermediate revisions by 2 users not shown)
Line 1: Line 1:
−
== Evaluation ==
+
== Analyzer Evaluation ==
  
−
* div.yaml: 102/124 of tests passed
+
* div.yaml: 155/265 tests passed
 +
* commonwords.yaml: 6/30 tests passed  
 +
* Number of Stems: 56
  
 
===Top Unknown Words===
 
===Top Unknown Words===
−
 
  
 
{|class="wikitable"
 
{|class="wikitable"
 
!Word !! Occurrences !! Gloss !! Tags  
 
!Word !! Occurrences !! Gloss !! Tags  
−
|-
 
−
|  ައް || 65 ||  || {{morphTest|{{tag|unk}}| ައް}}
 
 
|-  
 
|-  
 
| އަދި || 50 || "and" || {{morphTest|އަދި{{tag|cnjcoo}}|އަދި}}
 
| އަދި || 50 || "and" || {{morphTest|އަދި{{tag|cnjcoo}}|އަދި}}
Line 15: Line 14:
 
| ނުވަތަ || 47 || "or" || {{morphTest|ނުވަތަ{{tag|cnjcoo}}|ނުވަތަ}}
 
| ނުވަތަ || 47 || "or" || {{morphTest|ނުވަތަ{{tag|cnjcoo}}|ނުވަތަ}}
 
|-  
 
|-  
−
| ު || 39 || || {{morphTest|{{tag|unk}}| ު}}
+
| ޙައްޤު || 35 ||   || {{morphTest|ޙައްޤު{{tag|unk}}|ޙައްޤު}}
 
|-
 
|-
−
| ކޮންމެ || 32 || || {{morphTest|{{tag|unk}}|ކޮންމެ}}
+
| ކޮންމެ || 32 || "some, any" || {{morphTest|{{tag|unk}}|ކޮންމެ}}
 
|-
 
|-
 
| ލިބިގެންވެއެވެ || 30 ||  || {{morphTest|{{tag|unk}}|ލިބިގެންވެއެވެ}}
 
| ލިބިގެންވެއެވެ || 30 ||  || {{morphTest|{{tag|unk}}|ލިބިގެންވެއެވެ}}
 
|-
 
|-
−
| ވަނަ || 30 ||  || {{morphTest|{{tag|unk}}|ވަނަ}}
+
| ވަނަ || 30 || suffix "-vana" (-th) ordinal || {{morphTest|{{tag|unk}}|ވަނަ}}
 +
|-
 +
| މާތްﷲ || 30 ||  || {{morphTest|{{tag|unk}}|މާތްﷲ}}
 
|-
 
|-
−
| މާއްދާ || 29 || || {{morphTest|{{tag|unk}}|މާއްދާ}}
+
| މާއްދާ || 29 || "article" || {{morphTest|މާއްދާ{{tag|n}}{{tag|nHum}}{{tag|sg}}{{tag|def}}{{tag|dir}}|މާއްދާ}}
 
|-
 
|-
 
| މީހަކަށްމެ || 28 ||  || {{morphTest|{{tag|unk}}|މީހަކަށްމެ}}
 
| މީހަކަށްމެ || 28 ||  || {{morphTest|{{tag|unk}}|މީހަކަށްމެ}}
Line 34: Line 35:
 
|-
 
|-
 
| ހުރިހާ || 16 ||  || {{morphTest|{{tag|unk}}|ހުރިހާ}}
 
| ހުރިހާ || 16 ||  || {{morphTest|{{tag|unk}}|ހުރިހާ}}
−
|-
 
−
| އެ || 16 ||  || {{morphTest|{{tag|unk}}|އެ}}
 
 
|-
 
|-
 
| ލިބިގަތުމުގެ || 14 ||  || {{morphTest|{{tag|unk}}|ލިބިގަތުމުގެ}}
 
| ލިބިގަތުމުގެ || 14 ||  || {{morphTest|{{tag|unk}}|ލިބިގަތުމުގެ}}
Line 44: Line 43:
 
|-
 
|-
 
| އޭނާގެ || 14 ||  || {{morphTest|{{tag|unk}}|އޭނާގެ}}
 
| އޭނާގެ || 14 ||  || {{morphTest|{{tag|unk}}|އޭނާގެ}}
−
|-
 
−
| ތަ || 14 ||  || {{morphTest|{{tag|unk}}|ތަ}}
 
 
|}
 
|}
  
−
== Notes ==
+
=== Notes ===
  
 
The tests that still don't work are:
 
The tests that still don't work are:
  
−
# 1 test has a space in the word, and we're still not sure how to fix it.
 
−
# "the watermelons" failed because it is an irregular
 
 
# We're not sure how to deal with the "+".
 
# We're not sure how to deal with the "+".
−
 
  
 
=== Adding Unknown Words ===
 
=== Adding Unknown Words ===
  
 
By adding unknown words {{morphTest|އަދި{{tag|cnjcoo}}|އަދި}}, {{morphTest|ނުވަތަ{{tag|cnjcoo}}|ނުވަތަ}}, and {{morphTest|ހަމަ{{tag|adj}}|ހަމަ}}, the coverage went from 2.32% to 6.62%.
 
By adding unknown words {{morphTest|އަދި{{tag|cnjcoo}}|އަދި}}, {{morphTest|ނުވަތަ{{tag|cnjcoo}}|ނުވަތަ}}, and {{morphTest|ހަމަ{{tag|adj}}|ހަމަ}}, the coverage went from 2.32% to 6.62%.
 +
 +
By adding unknown word {{morphTest|މާއްދާ{{tag|n}}{{tag|sg}}|މާއްދާ}}, the coverage went from 6.62% to 7.90%.
 +
 +
== Genarator Evaluation ==
 +
 +
=== Initial Evaluation of Morphological Generation ===
 +
 +
Current Analyser Evaluation
 +
* Current number of tests passed (div.yaml): 155/265
 +
* Current corpus coverage (div.corpus.basic.txt): 7.90%
 +
 +
Current Generator Evaluation
 +
* Current number of tests passed (div.yaml): 81/144
 +
 +
=== Final Evaluation of Morphological Generation ===
 +
 +
* Current number of tests passed: 94/120 (morph-test.py -cl div.yaml)
 +
* Number of twol rules added:  20
 +
* Current corpus coverage (div.corpus.basic.txt): 24.14%
 +
 +
==== Note ====
 +
* I added punctuation to the lexc file and the coverage jumped from 8.51% to 23.82%.
  
 
== Github ==
 
== Github ==
  
 
[https://github.swarthmore.edu/Ling073-sp19/ling073-div Dhivehi Transducer]
 
[https://github.swarthmore.edu/Ling073-sp19/ling073-div Dhivehi Transducer]
 +
 +
[[Category:Sp19_Transducers]]
 +
[[Category:Dhivehi]]

Latest revision as of 04:56, 20 March 2019

Analyzer Evaluation

  • div.yaml: 155/265 tests passed
  • commonwords.yaml: 6/30 tests passed
  • Number of Stems: 56

Top Unknown Words

Word Occurrences Gloss Tags
އަދި 50 "and" އަދި<cnjcoo> ↔ އަދި
ނުވަތަ 47 "or" ނުވަތަ<cnjcoo> ↔ ނުވަތަ
ޙައްޤު 35 ޙައްޤު<unk> ↔ ޙައްޤު
ކޮންމެ 32 "some, any" <unk> ↔ ކޮންމެ
ލިބިގެންވެއެވެ 30 <unk> ↔ ލިބިގެންވެއެވެ
ވަނަ 30 suffix "-vana" (-th) ordinal <unk> ↔ ވަނަ
މާތްﷲ 30 <unk> ↔ މާތްﷲ
މާއްދާ 29 "article" މާއްދާ<n><nHum><sg><def><dir> ↔ މާއްދާ
މީހަކަށްމެ 28 <unk> ↔ މީހަކަށްމެ
ހަމަ 25 "just" ހަމަ<adj> ↔ ހަމަ
ދެން 24 <unk> ↔ ދެން
އެއްވެސް 20 <unk> ↔ އެއްވެސް
ހުރިހާ 16 <unk> ↔ ހުރިހާ
ލިބިގަތުމުގެ 14 <unk> ↔ ލިބިގަތުމުގެ
ނުވާނެއެވެ 14 <unk> ↔ ނުވާނެއެވެ
އެއީ 14 <unk> ↔ އެއީ
އޭނާގެ 14 <unk> ↔ އޭނާގެ

Notes

The tests that still don't work are:

  1. We're not sure how to deal with the "+".

Adding Unknown Words

By adding unknown words އަދި<cnjcoo> ↔ އަދި, ނުވަތަ<cnjcoo> ↔ ނުވަތަ, and ހަމަ<adj> ↔ ހަމަ, the coverage went from 2.32% to 6.62%.

By adding unknown word މާއްދާ<n><sg> ↔ މާއްދާ, the coverage went from 6.62% to 7.90%.

Genarator Evaluation

Initial Evaluation of Morphological Generation

Current Analyser Evaluation

  • Current number of tests passed (div.yaml): 155/265
  • Current corpus coverage (div.corpus.basic.txt): 7.90%

Current Generator Evaluation

  • Current number of tests passed (div.yaml): 81/144

Final Evaluation of Morphological Generation

  • Current number of tests passed: 94/120 (morph-test.py -cl div.yaml)
  • Number of twol rules added: 20
  • Current corpus coverage (div.corpus.basic.txt): 24.14%

Note

  • I added punctuation to the lexc file and the coverage jumped from 8.51% to 23.82%.

Github

Dhivehi Transducer