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 15:13] ptacek |
draft [2009/07/15 15:52] ptacek |
||
---|---|---|---|
Line 14: | Line 14: | ||
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 35: | Line 30: | ||
features: omit filler phrases, remove irrelevant speech events, handle false starts, repetitions, | features: omit filler phrases, remove irrelevant speech events, handle false starts, repetitions, | ||
performance indicator: BLEU score between actual output and manually reconstructed sentences from corpora (T5.2.1), baseline: Moses with default settings | 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) ===== | ===== Morphology Analyzer and POS tagging (WP 5.2) ===== | ||
- | features: coverage of photo-pal domain(PRIDA NAM JARKA SLOVA CO NAJDEME? | + | features: coverage of photo-pal domain, domain adapted tagger (XXX prida nam Jarka OOV slova co najdeme, bude PDTSC rucne oznackovane |
performance indicator: OOV rate, accuracy | performance indicator: OOV rate, accuracy | ||
+ | |||
+ | |||
===== 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 | ||
+ | ===== 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 106: | ||
+ | ===== advances ===== | ||
- | + | 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. | |
- | ===== Dialog Manager | + | pos ? analyzovat, generovat |
- | 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, Person_in_productive_age, Child, Husband, Wife, Wedding, Christmas, Handle_stalled_dialog | + | |
- | 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 | + |