Progress Report - dal jsem to na zvlastni stranku, abysme si nelezli do zeli

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). 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 enough package within time frame that allows for integration, © possibility of reusing DAF states, tests and specified actions for the upcoming statistical DM by UOXF (however this is post November work).

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.

features: improved language models, real-time speaker adaptation
performance indicator: WER

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

features: coverage of photo-pal domain, domain adapted tagger (XXX prida nam Jarka OOV slova co najdeme - Mirek uz vyrabi list, bude PDTSC rucne oznackovane - do listopadu?)
performance indicator: OOV rate, accuracy

features: induce dependencies and labels
performance indicator: accuracy (correctly induced edges, labels)

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)

features: template based identification of predicates
covering predicates from before-mentioned set of DAFs.
performance indicator: accuracy

features: detect person names, geographical locations, organization names
performance indicator: f-measure

features: domain tailored tag-set (variation of DAMSL-SWBD)
performance indicator: accuracy

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

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

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

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)

features: adapted to domain (McD trained on manual PDTSC trees)
performance indicator: accuracy (correctly induced edges, labels)

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

T5.2.7 tohle zminuje, nick webb to pro nas asi neudela
performance indicator: number of tokens in user reply utterances, post-session questionare

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?