[ 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 12:32]
ptacek 		draft [2009/08/31 14:28]
ptacek
Line 1: Line 1:
 ====== Progress Report ====== ====== Progress Report ======
  
 +[[Progress Report]] - dal jsem to na zvlastni stranku, abysme si nelezli do zeli
  
-Hi Marc, 
  
-...+[[http://72.55.153.148/mediawiki-1.8.2/index.php/CZ_Demo_%28November_2009%29_Specs_and_Components_%282009-07-17%29#Natural_Language_Generation_.28WP_5.4.29|final version of description]]
  
-Re: progress: there is progress in the following:+====== Description of Czech Companion November Demonstrator ======
  
-- speech re-training for the collected dialogue data +The Czech version of the 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 is different (see Figure 1). Regarding the physical settings, the Czech version runs on two notebook computers connected by a local network; one can be seen as a Speech Client, running modules dealing with ASR, TTS and ECA, second as an NLP Server.
-- additional dialogue transription for ASR is ongoing +
-- DM has been transferred from USFD to Prague (WP5.3) +
- being extensively tested +
-- DAF editor transfer is complete (WP5.3) +
-- Sample dialogues (specifically aimed at the demo) +
- are ready - issues are being resolved between CU/ZCU +
-- DAFs are being prepared for the SC-CZ scenario AND +
- the sample dialogues +
-- DA set is being prepared, also based on the sample dialogues (WP5.2) +
-- integration work is ongoing (CU/ZCU, internally at CU) +
- but no functioning full demo yet+
  
-I hope this is OK for the progress report. Pavel (I.) might add more specifics regarding the ASR and especially TTS progress.+The dialog is driven by a dialog manager component by USFD (originally developed for the English Senior Companion prototype), we supply the transition network (DAFs). The selection is backed by (a) appropriateness for the type of dialog we aim for (the corpus reveals frequent reoccurring topics to be handled by DAFs) , (b) availability of mature package within time frame that allows for integration, (c) possibility of reusing created DAF states, tests and specified actions for the upcoming statistical DM by UOXF (however this is post November work).
  
-Best,+Our DAFs covering selected topics contain not only Companion replies mined from the corpora, but also new human-authored assessments, remarks and glosses to provide longer system utterances in order to encourage user to tell more.
  
--- Jan+For a sample dialogue, see the Scenario Brief below. 
  
-====== Description of Czech Companion November Prototype ======+{{user:ptacek:czech_companion_diagram.png|}}
  
-The Czech version of Companion deals with the Reminiscing about User's Photos scenario.  
-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), 
-typy odpovedi a zpusob jejich implementace, rucne vyrobene dafy pro nasledujici topics: Person_Retired, Person_in_productive_age, Child, Husband, Wife, Wedding, Christmas, Handle_stalled_dialog 
-NLP server s tectomt, ASR/TTS/SR client, connected over network 
-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. +===== Automatic Speech Recognition (WP 5.1)===== 
-pos ? analyzovat, generovat a kontrolovat 'jen' kde je rozdil ve forme?+features: improved language models, real-time speaker adaptation 
 +performance indicator: WER 
  
  
-===== Speech Reconstruction ===== 
-features: omit filler phrases, irrelevant speech events, false starts, repetitions, corrections, syntax smoothing (WO,  
-imlementation(zahrnout tuhle info?): moses natrenovany na korpusu 
-performance indicator: BLEU score (overall scoring of all features) to annotated corpora from T5.2.1., nejaka baseline 
-XXX Mirek 
  
-===== Morphology Analyzer and POS tagging ===== 
-features: XXX Mirek/Johanka 
-performance indicator: accuracy 
  
-===== Syntactic Parsing =====+ 
 +===== Speech Reconstruction (WP 5.2) ===== 
 +features: omit filler phrases, remove irrelevant speech events, handle false starts, repetitions, and corrections, polish word ordering performance indicator: BLEU score between actual output and manually reconstructed sentences from corpora (T5.2.1), baseline: Moses with default settings  
 + 
 + 
 + 
 + 
 + 
 + 
 + 
 + 
 +===== Morphology Analyzer and POS tagging (WP 5.2) ===== 
 +features: coverage of photo-pal domain, domain adapted tagger 
 +performance indicator: OOV rate, accuracy  
 + 
 + 
 + 
 + 
 +===== Syntactic Parsing (WP 5.2) =====
 features: induce dependencies and labels features: induce dependencies and labels
-performance indicator: f-measure +performance indicator: accuracy (correctly induced edges, labels)
-v tipu je natrenovat MacDonnalda na dialog datech, ten task je do M42, ted ne.+
  
  
-===== Semantic Parsing ===== 
-features: meaning representation with semantic roles (69 labels), coordinations, argument structure, partial ellipsis resolution, pronominal anaphora resolution, 
-performance indicator: f-measure 
  
-===== Information Extraction =====+ 
 + 
 +===== Semantic Parsing (WP 5.2) ===== 
 +features: assignment of semantic roles (69 roles), coordinations, argument structure, partial ellipsis resolution, pronominal anaphora resolution, post parsing detection of ungrammatical edges (caused by long user utterances) 
 +performance indicator: accuracy (correctly induced edges, labels) 
 + 
 + 
 +===== Information Extraction (WP 5.2) =====
 features: template based identification of predicates features: template based identification of predicates
 covering predicates from  before-mentioned set of DAFs. covering predicates from  before-mentioned set of DAFs.
 performance indicator: accuracy performance indicator: accuracy
  
-===== Named Entities Recognition ===== + 
-features: detect person names, geographical locations (organizations jsou potreba?)+ 
 +===== Named Entities Recognition (WP 5.2) ===== 
 +features: detect person names, geographical locations, organization names
 performance indicator: f-measure performance indicator: f-measure
  
-===== Dialog Act Tagging ===== + 
-features: tagset derived from DAMSL-SWBD, DA is a key feature driving the decision, what to say next.+ 
 + 
 +===== Dialog Act Tagging (WP 5.2) ===== 
 +features: domain tailored tag-set (variation of DAMSL-SWBD)
 performance indicator: accuracy performance indicator: accuracy
  
  
-===== Sentiment Analysis ===== 
-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 ===== 
-T5.2.7 tohle zminuje, nick webb to pro nas asi neudela 
-performance indicator: pocet slov ve vypovedich uzivatele(?),  
  
  
  
  
-===== Dialog Manager ===== 
-features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) 
-performance indicator: rucni hodnoceni prijatelnosti vybrane akce 
  
-===== Natural Language Generation ===== +===== Dialog Manager (WP 5.3) ===== 
-features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech a templatech u hodnoticich vet)+features: integrated DAF-based dialog manager from previous English prototype, 
 +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 
 + 
 + 
 + 
 + 
 + 
 + 
 + 
 +===== Natural Language Generation (WP 5.4) ===== 
 +features: adding of functional words, morphological adjustments, generating paraphrases for hard-coded utterances, underspecified input (dott format).
 performance indicator: BLEU score performance indicator: BLEU score
 +
 +
 +
 +===== Emotional TTS (WP 5.5) =====
 +features: emotions will be expressed implicitly, through the usage of communicative functions; new female voice database was recorded for this purposes
 +performance indicator: listening tests 
 +
 +
 +
 +
 +===== Emotional Avatar Integration (WP 5.5) =====
 +features: new Czech female voice with affective features will be integrated with the TID avatar
 +performance indicator: subjective evaluation of the naturalness and the ability to convey emotions (small-scale, given the time constraint)
 +
 +
 +
 +====== Scenario Brief ======
 +
 +C1 Dobrý den, jak se jmenujete? (intro-daf-based)
 +H1 Marie.
 +
 +C2 Těší mě. Já jsem Pavla a chtěla bych Vás blíž poznat. Jsem ráda, že mi ukážete Vaše fotografie.
 +
 +C2 Co je tohle? (photo_maintenance)
 +H2 To je moje rodina, rodiče, sestra, její manžel, moje dvě děti a její dvě děti.
 +H2 Byli u mě na Vánoce na návštěvě.
 +
 +C3 Trávíte Vánoce takhle pohromadě?
 +H3 Teď už ne.
 +H3 Teď už všechny moje dětičky vylétaly z hnízda.
 +
 +C4 Jak se jmenuje váš manžel?
 +H4 Manžel už nežije, jmenoval se Karel Šístek.
 +
 +C5 Máte ráda Vánoce?
 +H5 Teď už ne.
 +H5 Měla jsem je ráda, když byly děti malé.
 +H5 Teď už to ale není ono.
 +
 +C6 Takže teď trávíte Vánoce sama? (ask_on_detail-daf-based)
 +H6 Nejsem úplně sama, chodím každé Vánoce k dceři, ale už to není, jak to bývalo, když byly doma malé děti.
 +
 +C7 Jak děti vyrostou, tak má člověk najednou příliš mnoho času.
 +C7 Kdo je kdo na té fotce?
 +H7 U stromečku je můj synovec, ta holčička vedle je moje dcera, chlapeček s hračkou je můj syn, vedle je sestra, její manžel a nad ním je můj otec.
 +
 +C8 To jste ale velká rodina.
 +C8 Jak se jmenuje vaše sestra? (companion commenting last utterance  bundled with follow-up question - to achieve longer responses)
 +H8 Sestra se jmenuje Marie Havlová, její manžel je Vladimír, ten bohužel nedávno zemřel.
 +
 +C9 To je smutné.
 +C9 Znala jste ho dobře?
 +H9 Velmi dobře, trávili jsme obě rodiny společně hodně času.
 +
 +C10 Máte už nějaká vnoučata?
 +H10 Mám vnučku Natálku.
 +H10 Ona je takové živé děťátko, taková neposeda.
 +
 +C11 Takže Natálka je neposeda. repeat-rephrase
 +C11 Máte ještě nějaké další vnučky nebo vnuky?
 +H11 Čekáme ještě další přírustek.
 +
 +C12 Hlídáte je někdy?
 +H12 Hlídám dost často.
 +H12 Já mám děti ráda a jsem s nimi moc ráda.
 +
 +C13 To je fajn.
 +C13 S dětmi je legrace.
 +H13 Ano.
 +
 +C Podíváme se na další fotku?
 +
 +

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