Difference between revisions of "Berik/Transducer"

From LING073
Jump to: navigation, search
(Created page with "Code: [https://github.swarthmore.edu/jspring1/ling073-bkl https://github.swarthmore.edu/jspring1/ling073-bkl] == Evaluation == * Current corpus coverage: 34.65% * Number of...")
 
Line 5: Line 5:
 
* Current corpus coverage: 34.65%
 
* Current corpus coverage: 34.65%
 
* Number of stems: UNKNOWN
 
* Number of stems: UNKNOWN
* Top unknown words: TODO
+
* Top unknown words:
* Analyzer tests passing: 85
+
** jei (84)
* Generator tests passing: 85
+
** aa (64)
* Corpus tests passing: UNKNOWN
+
** jeta (42)
 +
** jeiserem (36)
 +
** Jei (35)
 +
** ge (31)
 +
** taterisi (11)
 +
** aane (11)
 +
** jebe (9)
 +
** bosna (9)
 +
** anes (9)
 +
** asal (8)
 +
** asala (8)
 +
** Aamai (8)
 +
** temawer (8)
 +
** Jepga (8)
 +
** aaiserem (8)
 +
** enggame (7)
 +
** Taterisi (7)
 +
** Sanbagiri (6)
 +
* Analyzer tests passing: 85/117 (72.65%)
 +
* Generator tests passing: 85/152 (55.92%)
 +
* Corpus tests passing: 14/33 (42.42%)
  
 
== Notes ==
 
== Notes ==
Line 14: Line 34:
 
Initial corpus coverage was 21.98%.
 
Initial corpus coverage was 21.98%.
  
Coverage was raised to 34.65% by adding {{morphTest|jamere{{tag|locl}}|jamere}},
+
Coverage was raised to 34.65% by adding
{{morphTest|Yesus{{tag|n}}|Yesus}},
+
* {{morphTest|jamere{{tag|locl}}|jamere}}
{{morphTest|Yusuf{{tag|n}}|Yusuf}},
+
* {{morphTest|Yesus{{tag|n}}|Yesus}}
{{morphTest|Maria{{tag|n}}|Maria}},
+
* {{morphTest|Yusuf{{tag|n}}|Yusuf}}
{{morphTest|Daud{{tag|n}}|Daud}},
+
* {{morphTest|Maria{{tag|n}}|Maria}}
{{morphTest|angtane{{tag|n}}|angtane}},
+
* {{morphTest|Daud{{tag|n}}|Daud}}
{{morphTest|raja{{tag|n}}|raja}},
+
* {{morphTest|angtane{{tag|n}}|angtane}}
{{morphTest|taman{{tag|n}}|taman}},
+
* {{morphTest|raja{{tag|n}}|raja}}
{{morphTest|kapka{{tag|adj}}|kapka}},
+
* {{morphTest|taman{{tag|n}}|taman}}
{{morphTest|se{{tag|imp}}|se}},
+
* {{morphTest|kapka{{tag|adj}}|kapka}}
{{morphTest|je{{tag|prn}}{{tag|pos}}|jemna}},
+
* {{morphTest|se{{tag|imp}}|se}}
{{morphTest|je{{tag|prn}}{{tag|subj}}|jam}},
+
* {{morphTest|je{{tag|prn}}{{tag|pos}}|jemna}}
{{morphTest|je{{tag|prn}}+wer{{tag|post}}|jewer}},
+
* {{morphTest|je{{tag|prn}}{{tag|subj}}|jam}}
{{morphTest|gam{{tag|part}}|gam}}.
+
* {{morphTest|je{{tag|prn}}+wer{{tag|post}}|jewer}}
 +
* {{morphTest|gam{{tag|part}}|gam}}

Revision as of 11:14, 1 March 2018

Code: https://github.swarthmore.edu/jspring1/ling073-bkl

Evaluation

  • Current corpus coverage: 34.65%
  • Number of stems: UNKNOWN
  • Top unknown words:
    • jei (84)
    • aa (64)
    • jeta (42)
    • jeiserem (36)
    • Jei (35)
    • ge (31)
    • taterisi (11)
    • aane (11)
    • jebe (9)
    • bosna (9)
    • anes (9)
    • asal (8)
    • asala (8)
    • Aamai (8)
    • temawer (8)
    • Jepga (8)
    • aaiserem (8)
    • enggame (7)
    • Taterisi (7)
    • Sanbagiri (6)
  • Analyzer tests passing: 85/117 (72.65%)
  • Generator tests passing: 85/152 (55.92%)
  • Corpus tests passing: 14/33 (42.42%)

Notes

Initial corpus coverage was 21.98%.

Coverage was raised to 34.65% by adding

  • jamere<locl> ↔ jamere
  • Yesus<n> ↔ Yesus
  • Yusuf<n> ↔ Yusuf
  • Maria<n> ↔ Maria
  • Daud<n> ↔ Daud
  • angtane<n> ↔ angtane
  • raja<n> ↔ raja
  • taman<n> ↔ taman
  • kapka<adj> ↔ kapka
  • se<imp> ↔ se
  • je<prn><pos> ↔ jemna
  • je<prn><subj> ↔ jam
  • je<prn>+wer<post> ↔ jewer
  • gam<part> ↔ gam