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 [2009/07/15 14:38] ptacek |
draft [2009/07/15 15:59] ptacek |
||
---|---|---|---|
Line 7: | Line 7: | ||
====== Description of Czech Companion November Prototype ====== | ====== Description of Czech Companion November Prototype ====== | ||
- | The Czech version of Companion deals with the Reminiscing about User's Photos scenario taking advantage of date 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: | ||
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' | 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' | ||
- | typy odpovedi a zpusob jejich implementace, | + | typy odpovedi a zpusob jejich implementace, |
NLP server s tectomt, ASR/TTS/SR client, connected over network | NLP server s tectomt, ASR/TTS/SR client, connected over network | ||
XXX JPta | XXX JPta | ||
- | |||
- | advances in Czech NLU (on reconstructed spoken data): 300-500vet(? | ||
- | pos ? analyzovat, generovat a kontrolovat ' | ||
- | |||
- | |||
Line 28: | Line 21: | ||
features: improved language models, real-time speaker adaptation | features: improved language models, real-time speaker adaptation | ||
performance indicator: WER | performance indicator: WER | ||
+ | |||
+ | |||
+ | |||
===== Speech Reconstruction (WP 5.1 ???) ===== | ===== Speech Reconstruction (WP 5.1 ???) ===== | ||
- | features: omit filler phrases, irrelevant speech events, false starts, repetitions, | + | features: omit filler phrases, |
- | imlementation(zahrnout tuhle info?): moses natrenovany na korpusu | + | performance indicator: BLEU score between actual output and manually reconstructed sentences from corpora |
- | performance indicator: BLEU score (overall scoring of all features) to annotated corpora from T5.2.1., nejaka | + | |
- | XXX Mirek | + | |
+ | |||
+ | |||
===== Morphology Analyzer and POS tagging (WP 5.2) ===== | ===== Morphology Analyzer and POS tagging (WP 5.2) ===== | ||
- | features: XXX Mirek/ | + | features: |
- | performance indicator: accuracy | + | performance indicator: |
+ | |||
===== Syntactic Parsing (WP 5.2) ===== | ===== Syntactic Parsing (WP 5.2) ===== | ||
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, ted ne. | v tipu je natrenovat MacDonnalda na dialog datech, ten task je do M42, ted ne. | ||
+ | |||
+ | |||
===== Semantic Parsing (WP 5.2) ===== | ===== Semantic Parsing (WP 5.2) ===== | ||
- | features: | + | features: |
- | performance indicator: | + | performance indicator: |
===== Information Extraction (WP 5.2) ===== | ===== Information Extraction (WP 5.2) ===== | ||
Line 56: | Line 59: | ||
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 (WP 5.2) ===== | ===== Named Entities Recognition (WP 5.2) ===== | ||
- | features: detect person names, geographical locations | + | features: detect person names, geographical locations, organizations |
performance indicator: f-measure | performance indicator: f-measure | ||
+ | |||
+ | |||
+ | |||
===== Dialog Act Tagging (WP 5.2) ===== | ===== Dialog Act Tagging (WP 5.2) ===== | ||
- | features: tagset | + | features: |
performance indicator: accuracy | performance indicator: accuracy | ||
- | ===== Sentiment Analysis (WP 5.2) ===== | ||
- | features: za tohle bych vydaval klasifikator, | ||
- | performance indicator: f-measure | ||
Line 75: | Line 79: | ||
+ | ===== Dialog Manager (WP 5.3) ===== | ||
+ | features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) | ||
+ | Manually created DAFs covering following topics: Person_Retired, | ||
+ | performance indicator: acceptability - manual evaluation of actions selected by DM | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | ===== Natural Language Generation (WP 5.4) ===== | ||
+ | features: morphological adjustments, | ||
+ | performance indicator: BLEU score | ||
+ | |||
+ | |||
+ | ====== 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 ===== | ||
Line 81: | Line 108: | ||
+ | ===== advances ===== | ||
- | + | advances in Czech NLU (on reconstructed spoken data): 300-500vet(?) rucne anotovat pos, a-tree, t-tree, IE predicates, | |
- | ===== Dialog Manager | + | pos ? analyzovat, generovat |
- | features: reply types, using (language independed) predicates | + | |
- | performance indicator: rucni hodnoceni prijatelnosti vybrane akce | + | |
- | + | ||
- | ===== Natural Language Generation (WP 5.4) ===== | + | |
- | features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech | + | |
- | performance indicator: BLEU score | + |