Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
draft [2009/07/14 16:09] ptacek |
draft [2009/07/15 23:13] ptacek |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== | + | ====== |
- | 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' | + | [[Progress Report]] - dal jsem to na zvlastni stranku, abysme si nelezli |
- | typy odpovedi a zpusob jejich implementace, | + | |
- | NLP server s tectomt, ASR/TTS/SR client, connected over network | + | |
- | XXX JPta | + | |
- | advances in Czech NLU (on reconstructed spoken data): 100vet(?) rucne anotovat pos, a-tree, t-tree, IE predicates, Named Entities, DA pro eval in-domain testy | ||
- | pos ? analyzovat, generovat a kontrolovat ' | ||
- | ===== Speech Reconstruction ===== | + | ====== Description of Czech Companion November Demostrator ====== |
- | features: omit filler phrases, irrelevant speech events, false starts, repetitions, | + | |
- | imlementation(zahrnout tuhle info?): moses natrenovany na korpusu | + | 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. |
- | performance indicator: BLEU score (overall scoring of all features) to annotated corpora | + | |
- | XXX Mirek | + | 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, |
+ | |||
+ | {{user: | ||
+ | |||
+ | |||
+ | ===== Automatic Speech Recognition (WP 5.1)===== | ||
+ | features: improved language models, real-time speaker adaptation | ||
+ | performance indicator: WER | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | ===== Speech Reconstruction | ||
+ | features: omit filler phrases, | ||
+ | performance indicator: BLEU score between actual output and manually reconstructed sentences | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | ===== Morphology Analyzer and POS tagging (WP 5.2) ===== | ||
+ | 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 | ||
+ | |||
- | ===== Morphology Analyzer and POS tagging ===== | ||
- | features: XXX Mirek/ | ||
- | performance indicator: accuracy | ||
- | ===== Syntactic Parsing ===== | + | ===== Syntactic Parsing |
features: induce dependencies and labels | features: induce dependencies and labels | ||
- | performance indicator: | + | performance indicator: |
- | v tipu je natrenovat MacDonnalda na dialog datech, ten task je do M42, ze bysme | + | |
- | ===== Semantic Parsing ===== | ||
- | features: meaning representation with semantic roles (69 labels), coordinations, | ||
- | performance indicator: f-measure | ||
- | ===== Information Extraction ===== | + | |
+ | |||
+ | ===== Semantic Parsing (WP 5.2) ===== | ||
+ | features: assignment of semantic roles (69 roles), coordinations, | ||
+ | performance indicator: accuracy (correctly induced edges, labels) | ||
+ | |||
+ | ===== Information Extraction | ||
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 | + | |
+ | ===== Named Entities Recognition | ||
+ | features: detect person names, geographical locations, organizations | ||
performance indicator: f-measure | performance indicator: f-measure | ||
- | ===== Dialog Act Tagging ===== | ||
- | features: tagset derived from DAMSL-SWBD, DA is a key feature driving | ||
- | performance indicator: | ||
- | ===== Sentiment Analysis ===== | ||
- | features: | ||
- | performance indicator: | ||
+ | |||
+ | ===== Dialog Act Tagging (WP 5.2) ===== | ||
+ | features: domain tailored tagset (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, | ||
+ | performance indicator: acceptability - manual evaluation of actions selected by DM | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | |||
+ | ===== Natural Language Generation (WP 5.4) ===== | ||
+ | features: adding of functional words, morphological adjustments, | ||
+ | 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 | ||
+ | perfomance 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, | ||
+ | |||
+ | |||
+ | ====== 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, | ||
+ | performance indicator: f-measure | ||
===== Complete System Evaluation ===== | ===== Complete System Evaluation ===== | ||
T5.2.7 tohle zminuje, nick webb to pro nas asi neudela | T5.2.7 tohle zminuje, nick webb to pro nas asi neudela | ||
- | performance indicator: | + | performance indicator: |
- | ===== Dialog Manager | + | |
- | features: reply types, using (language independed) predicates | + | ===== advances |
- | performance indicator: rucni hodnoceni prijatelnosti vypovedi | + | |
- | + | advances in Czech NLU (on reconstructed spoken data): 300-500vet(?) rucne anotovat pos, a-tree, t-tree, IE predicates, | |
- | ===== Natural Language Generation ===== | + | pos ? analyzovat, generovat |
- | features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech | + | |
- | performance indicator: BLEU score | + |