[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » draft

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
Next revision Both sides next revision
draft [2009/07/15 15:39]
ptacek 		draft [2009/07/15 15:59]
ptacek
Line 14: Line 14:
 NLP server s tectomt, ASR/TTS/SR client, connected over network NLP server s tectomt, ASR/TTS/SR client, connected over network
 XXX JPta XXX JPta
- 
-advances in Czech NLU (on reconstructed spoken data): 300-500vet(?) rucne anotovat pos, a-tree, t-tree, IE predicates, Named Entities, DA pro eval in-domain testy after Nov. 
-pos ? analyzovat, generovat a kontrolovat 'jen' kde je rozdil ve forme? 
- 
- 
  
  
Line 44: Line 39:
 features: coverage of photo-pal domain, domain adapted tagger (XXX prida nam Jarka OOV slova co najdeme, bude PDTSC rucne oznackovane - do listopadu?) features: coverage of photo-pal domain, domain adapted tagger (XXX prida nam Jarka OOV slova co najdeme, bude PDTSC rucne oznackovane - do listopadu?)
 performance indicator: OOV rate, accuracy performance indicator: OOV rate, accuracy
 +
  
  
Line 78: Line 74:
  
  
-===== Sentiment Analysis (WP 5.2) ===== 
-features: za tohle bych vydaval klasifikator, co rozhoduje ,jestli se rekne 'To je smutné/veselé'. Tem adjektivum rucne priradim negative/positive sentiment. 
-performance indicator: f-measure 
  
  
Line 86: Line 79:
  
  
 +===== Dialog Manager (WP 5.3) =====
 +features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky)
 +Manually created DAFs covering following topics: Person_Retired, Person_in_productive_age, Child, Husband, Wife, Wedding, Death, Christmas, Handle_stalled_dialog (most frequent topics in corpora)
 +performance indicator: acceptability - manual evaluation of actions selected by DM
  
 +
 +
 +
 +===== Natural Language Generation (WP 5.4) =====
 +features: morphological adjustments, generating paraphrases for hard-coded utterances, underspecified input (dott format), passing-through emotional markup (natvrdo v dafech a templatech u hodnoticich vet)
 +performance indicator: BLEU score
 +
 +
 +====== AZ PO LISTOPADU ======
 +
 +===== Syntactic Parsing (WP 5.2) =====
 +features: adapted to domain (McD trained on manual PDTSC trees)
 +performance indicator: accuracy (correctly induced edges, labels)
 +
 +
 +===== Sentiment Analysis (WP 5.2) =====
 +features: za tohle bych vydaval klasifikator, co rozhoduje ,jestli se rekne 'To je smutné/veselé'. Tem adjektivum rucne priradim negative/positive sentiment.
 +performance indicator: f-measure
  
 ===== Complete System Evaluation ===== ===== Complete System Evaluation =====
Line 93: Line 108:
  
  
 +===== advances =====
  
- +advances in Czech NLU (on reconstructed spoken data): 300-500vet(?) rucne anotovat pos, a-tree, t-tree, IE predicates, Named Entities, DA pro eval in-domain testy after Nov. 
-===== Dialog Manager (WP 5.3) ===== +pos ? analyzovat, generovat a kontrolovat 'jen' kde je rozdil ve forme?
-features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) +
-Handmade DAF covering following topics: Person_Retired, Person_in_productive_age, Child, Husband, Wife, Wedding, Christmas, Handle_stalled_dialog +
-performance indicator: rucni hodnoceni prijatelnosti vybrane akce +
- +
-===== Natural Language Generation (WP 5.4) ===== +
-features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech a templatech u hodnoticich vet) +
-performance indicator: BLEU score+

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