Detail publikace

Probability-Aware Word-Confusion-Network-to-Text Alignment Approach for Intent Classification

VILLATORO-TELLO, E. MADIKERI, S. SHARMA, B. KHALIL, D. KUMAR, S. NIGMATULINA, I. MOTLÍČEK, P. GANAPATHIRAJU, A.

Originální název

Probability-Aware Word-Confusion-Network-to-Text Alignment Approach for Intent Classification

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

Spoken Language Understanding (SLU) technologies have greatly improved due to the effective pretraining of speech representations. A common requirement of industry-based solutions is the portability to deploy SLU models in voice- assistant devices. Thus, distilling knowledge from large text- based language models has become an attractive solution for achieving good performance and guaranteeing portability. In this paper, we introduce a novel architecture that uses a cross- modal attention mechanism to extract bin-level contextual embeddings from a word-confusion network (WNC) encod- ing such that these can be directly compared and aligned with traditional text-based contextual embeddings. This alignment is achieved using a recently proposed tokenwise constrastive loss function. We validate our architecture's effectiveness by fine-tuning our WCN-based pretrained model to do intent classification (IC) on the well-known SLURP dataset. Ob- tained accuracy on the IC task (81%), depicts a 9.4% relative improvement compared to a recent/equivalent E2E method

Klíčová slova

Word-Confusion-Networks, Cross-modal Alignment, Knowledge Distillation, Intent Classification

Autoři

VILLATORO-TELLO, E.; MADIKERI, S.; SHARMA, B.; KHALIL, D.; KUMAR, S.; NIGMATULINA, I.; MOTLÍČEK, P.; GANAPATHIRAJU, A.

Vydáno

14. 4. 2024

Nakladatel

IEEE Signal Processing Society

Místo

Seoul

ISBN

979-8-3503-4485-1

Kniha

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Strany od

12617

Strany do

12621

Strany počet

5

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10445934

BibTex

@inproceedings{BUT196786,
  author="VILLATORO-TELLO, E. and MADIKERI, S. and SHARMA, B. and KHALIL, D. and KUMAR, S. and NIGMATULINA, I. and MOTLÍČEK, P. and GANAPATHIRAJU, A.",
  title="Probability-Aware Word-Confusion-Network-to-Text Alignment Approach for Intent Classification",
  booktitle="ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
  year="2024",
  pages="12617--12621",
  publisher="IEEE Signal Processing Society",
  address="Seoul",
  doi="10.1109/ICASSP48485.2024.10445934",
  isbn="979-8-3503-4485-1",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10445934"
}

Dokumenty

villatoro-tello_icassp2024_Probability-Aware_Word-Confusion-Network-To-Text_Alignment_Approach_for_Intent_Classification.pdf