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 13:09] 147.228.47.142 stará verze byla obnovena |
draft [2009/07/15 15:14] ptacek |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== Progress Report ====== | ====== Progress Report ====== | ||
+ | [[Progress Report]] - dal jsem to na zvlastni stranku, abysme si nelezli do zeli | ||
- | Hi Marc, | ||
- | ... | ||
- | Re: progress: there is progress in the following: | + | ====== Description of Czech Companion November Prototype ====== |
- | - language model re-training for the collected dialogue | + | 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 |
- | - additional dialogue transription for ASR is ongoing (WP52.? T5.2.1) | + | however the set of modules differs |
- | - DM has been transferred from USFD to Prague | + | |
- | 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) | + | |
- | - preliminary DA tagger (on std DAMSL-SWBD tagset) working (~35% error rate) (WP5.2) | + | |
- | - integration work is ongoing (CU/ZCU, internally at CU) | + | |
- | but no functioning full demo yet (beyond what we've presented in Madrid) | + | |
- | I hope this is OK for the progress report. Pavel (I.) might add more specifics regarding | + | 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, | ||
+ | NLP server s tectomt, ASR/TTS/SR client, connected over network | ||
+ | XXX JPta | ||
- | Best, | + | advances in Czech NLU (on reconstructed spoken data): 300-500vet(? |
+ | pos ? analyzovat, generovat a kontrolovat ' | ||
- | -- Jan | ||
Line 32: | Line 23: | ||
- | ====== Description of Czech Companion November Prototype ====== | + | ===== Automatic Speech Recognition (WP 5.1)===== |
+ | features: improved language models, real-time speaker adaptation | ||
+ | performance indicator: WER | ||
- | 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; | ||
- | however the set of modules differs (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 a NLP Server. | ||
- | 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, | ||
- | NLP server s tectomt, ASR/TTS/SR client, connected over network | ||
- | XXX JPta | ||
- | advances in Czech NLU (on reconstructed spoken data): 300-500vet(? | ||
- | pos ? analyzovat, generovat a kontrolovat ' | ||
- | ===== Speech Reconstruction ===== | ||
- | features: omit filler phrases, irrelevant speech events, false starts, repetitions, | ||
- | 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 | + | ===== Speech Reconstruction (WP 5.1 ???) ===== |
- | features: | + | features: |
- | performance indicator: | + | performance indicator: |
- | ===== Syntactic Parsing ===== | + | |
+ | |||
+ | |||
+ | |||
+ | ===== Morphology Analyzer and POS tagging (WP 5.2) ===== | ||
+ | features: coverage of photo-pal domain, domain adapted tagger PRIDA NAM JARKA SLOVA CO NAJDEME?, JEN V PRIPADE RUCNI ANOTACE COMPANIONS-PDTSC DO LISTOPADU | ||
+ | performance indicator: OOV rate, accuracy | ||
+ | |||
+ | ===== Syntactic Parsing | ||
features: induce dependencies and labels | features: induce dependencies and labels | ||
performance indicator: f-measure | performance indicator: f-measure | ||
Line 63: | Line 51: | ||
- | ===== Semantic Parsing ===== | + | ===== Semantic Parsing |
features: meaning representation with semantic roles (69 roles), coordinations, | features: meaning representation with semantic roles (69 roles), coordinations, | ||
performance indicator: f-measure | performance indicator: f-measure | ||
- | ===== Information Extraction ===== | + | ===== 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. | ||
Line 73: | Line 61: | ||
- | ===== Named Entities Recognition ===== | + | ===== Named Entities Recognition |
features: detect person names, geographical locations (organizations myslim nepotrebne) | features: detect person names, geographical locations (organizations myslim nepotrebne) | ||
performance indicator: f-measure | performance indicator: f-measure | ||
- | ===== Dialog Act Tagging ===== | + | ===== Dialog Act Tagging |
features: tagset derived from DAMSL-SWBD, DA is a key feature driving the decision, what to say next. | features: tagset derived from DAMSL-SWBD, DA is a key feature driving the decision, what to say next. | ||
performance indicator: accuracy | performance indicator: accuracy | ||
- | ===== Sentiment Analysis ===== | + | ===== Sentiment Analysis |
features: za tohle bych vydaval klasifikator, | features: za tohle bych vydaval klasifikator, | ||
performance indicator: f-measure | performance indicator: f-measure | ||
+ | |||
+ | |||
+ | |||
Line 90: | Line 81: | ||
===== 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 ===== | + | ===== Dialog Manager |
features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) | features: reply types, using (language independed) predicates (prakticky to znamena, ze pojmenuju testy na prechodech v dafech anglicky) | ||
+ | Handmade DAF covering following topics: Person_Retired, | ||
performance indicator: rucni hodnoceni prijatelnosti vybrane akce | performance indicator: rucni hodnoceni prijatelnosti vybrane akce | ||
- | ===== Natural Language Generation ===== | + | ===== Natural Language Generation |
features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech a templatech u hodnoticich vet) | features: variations, underspecified input (dott format), emotional markup (natvrdo v dafech a templatech u hodnoticich vet) | ||
performance indicator: BLEU score | performance indicator: BLEU score |