Differences

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

--- user:ptacek:dbmt [2007/05/07 19:14]
ptacek
+++ user:ptacek:dbmt [2007/05/07 19:41]
ptacek
@@ Line 4: / Line 4: @@
 je to Magenta pipeline, jen generovani je rule-based misto statistikeho tree-to-tree transducing a pak LM
-  - determining contextual boundness \\ delaji v CZ od slovesa vlevo zapojene, od slovesa vpravo nezapojene -> indefinite article
+  * na českém prekladu Penn Treebanku
-  - reordering of constituents
+  - tokenizace a tagging  [Hajic 98]
-  - generation of verb forms
+  - parsing do a_trees [Hajic 98, Charniak 99]
-  - insertion of prepositions and articles
+  - afun assigment [ZZ 02]
-  - morphology
+  - a_tree -> t_tree [Bohmova 01]
+  - func assigment C4.5 [ZZ 02]
+  - slovnik pomoci GIZA++ [Och and Nay 02] // one most probable translation, 1-2 as 1-1 multiword
+====== Generator ======
+dostane TGTS bez tfa, a co koreference :?:
+== 1. determining contextual boundness ==
+povazuji v CZ od slovesa vlevo jako CB -> definite article
+od slovesa vpravo nezapojene -> indefinite article
+== 2. reordering of constituents ==
+podle CB se z ACT|PAT|ADDR vyberou Sb
+declarative sentence: CB adjuncts + Sb + V + direct/indirect Obj + UB adjuncts
+== 3. generation of verb forms ==
+pasivum/aktivum se dela podle Sb funktoru
+== 4. insertion of prepositions and articles ==
+preps: podle české a podle EN nounu
+articles: definite při postmodified NP, premodified by superlative or ordinal num
+article prevented: uncountable + proper nouns nebo predetermination by possessive a demonstrative pronouns
+== 5. morphology ==
+asi ne morpha :!:
+hledaji v tabulce
+^ word form ^ morphological tag ^ lemma ^
+kdyz nenajdou tak somple rules
+taky vokalizace pro indefinite article

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

Institute of Formal and Applied Linguistics Wiki

Differences