[ 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 16:00]
ptacek 		draft [2009/07/15 16:20]
ptacek
Line 9: Line 9:
 The Czech version of Companion deals with the Reminiscing about User's Photos scenario taking advantage of data recorded in first phase of the project. The basic architecture is same as of the English version, i.e. set of modules communicating through the Inamode Relayer (TID) backbone; The Czech version of Companion deals with the Reminiscing about User's Photos scenario taking advantage of data recorded in first phase of the project. The basic architecture is same as of the English version, i.e. set of modules communicating through the Inamode Relayer (TID) backbone;
 however the set of modules differs (see Figure 1). Regarding the physical settings: the Czech version runs on two notebook computers connected by local network; one can be seen as a Speech Client, running modules dealing with ASR,TTS and ECA, second as an NLP Server. however the set of modules differs (see Figure 1). Regarding the physical settings: the Czech version runs on two notebook computers connected by local network; one can be seen as a Speech Client, running modules dealing with ASR,TTS and ECA, second as an NLP Server.
 +
 +{{user:ptacek:czech_companion_diagram.png.jpg|}}
  
 photopal domena, nahranej korpus, ze na to sou dafy (reusing SHEFF DM intergrated through Inamode Relayer (TID)) vhodny, moreover reusable for expected pomdp DM from UOX (reuse states, let pomdp's do the topology and handle the states transitions, post november work), photopal domena, nahranej korpus, ze na to sou dafy (reusing SHEFF DM intergrated through Inamode Relayer (TID)) vhodny, moreover reusable for expected pomdp DM from UOX (reuse states, let pomdp's do the topology and handle the states transitions, post november work),
Line 72: Line 74:
 features: domain tailored tagset (variation of DAMSL-SWBD) features: domain tailored tagset (variation of DAMSL-SWBD)
 performance indicator: accuracy performance indicator: accuracy
 +
  
  
Line 80: Line 83:
  
 ===== Dialog Manager (WP 5.3) ===== ===== Dialog Manager (WP 5.3) =====
-features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) +features: integrated DAF-based dialog manager from previous English prototype, 
-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)+manual creation of DAFs covering following topics: Person_retired, Person_in_productive_age, Child, Husband, Wife, Wedding, Christmas, Death, Handling_stalled_dialog (most frequent topics in corpora), using customized DAF Editor provided by USFD.
 performance indicator: acceptability - manual evaluation of actions selected by DM performance indicator: acceptability - manual evaluation of actions selected by DM
 +
  
  
Line 88: Line 92:
  
 ===== Natural Language Generation (WP 5.4) ===== ===== 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)+features: adding of functional words, morphological adjustments, generating paraphrases for hard-coded utterances, underspecified input (dott format), passing-through of emotional markup (originating in DAFs)
 performance indicator: BLEU score performance indicator: BLEU score
  
Line 111: Line 115:
  
 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. 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?+pos ? analyzovat, generovat a kontrolovat 'jen' kde je rozdil ve forme?{{user:ptacek:czech_companion_diagram.png.jpg|}}

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