Word-Semantic Lattices for Spoken Language Understanding

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F15%3A43926626" target="_blank" >RIV/49777513:23520/15:43926626 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7178976&tag=1" target="_blank" >http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7178976&tag=1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2015.7178976" target="_blank" >10.1109/ICASSP.2015.7178976</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Word-Semantic Lattices for Spoken Language Understanding

Popis výsledku v původním jazyce

The paper presents a method for converting word-based automatic speech recognition (ASR) lattices into word-semantic (W-SE) lattices that contain original words together with a partial semantic information – so-called semantic entities. Semantic entity detection algorithm generates semantic entities based on the expert-defined knowledge. The generated W-SE lattices have smaller vocabulary and consequently reduce the sparsity of the training data. The format of the W-SE lattices also naturally preserves the inherent uncertainty of the ASR output that can be exploited in subsequent dialog modules. The presented technique employs the framework of weighted finite state transducers which allows for efficient optimization of word-semantic lattices. We have evaluated the method in two different spoken language understanding tasks and obtained more than 10% reduction of concept error rate in comparison with using 1-best word hypothesis in both of those tasks.

Název v anglickém jazyce

Word-Semantic Lattices for Spoken Language Understanding

Popis výsledku anglicky

The paper presents a method for converting word-based automatic speech recognition (ASR) lattices into word-semantic (W-SE) lattices that contain original words together with a partial semantic information – so-called semantic entities. Semantic entity detection algorithm generates semantic entities based on the expert-defined knowledge. The generated W-SE lattices have smaller vocabulary and consequently reduce the sparsity of the training data. The format of the W-SE lattices also naturally preserves the inherent uncertainty of the ASR output that can be exploited in subsequent dialog modules. The presented technique employs the framework of weighted finite state transducers which allows for efficient optimization of word-semantic lattices. We have evaluated the method in two different spoken language understanding tasks and obtained more than 10% reduction of concept error rate in comparison with using 1-best word hypothesis in both of those tasks.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

ISBN

978-1-4673-6997-8

ISSN

1520-6149

e-ISSN

—

Počet stran výsledku

5

Strana od-do

5266-5270

Název nakladatele

IEEE

Místo vydání

New York

Místo konání akce

Brisbane, Australia

Datum konání akce

19. 4. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000427402905077