This is an old revision of the document!
Table of Contents
Progress Report
Progress Report - dal jsem to na zvlastni stranku, abysme si nelezli do zeli
Description of Czech Companion November Demonstrator
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.
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, © possibility of reusing created DAF states, tests and specified actions for the upcoming statistical DM by UOXF (however this is post November work).
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.
For a sample dialogue, see the Scenario Brief below.
Automatic Speech Recognition (WP 5.1)
features: improved language models, real-time speaker adaptation
performance indicator: WER
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
performance indicator: accuracy (correctly induced edges, labels)
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
covering predicates from before-mentioned set of DAFs.
performance indicator: accuracy
Named Entities Recognition (WP 5.2)
features: detect person names, geographical locations, organization names
performance indicator: f-measure
Dialog Act Tagging (WP 5.2)
features: domain tailored tag-set (variation of DAMSL-SWBD)
performance indicator: accuracy
Dialog Manager (WP 5.3)
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
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?