Descripción
|
|
---|---|
We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data. Compared to the state-ofthe- art methods, our approach does not require label embeddings as part of the input and therefore lends itself nicely to a wide range of model architectures. In addition, our architecture computes contextual distances between words and labels to avoid adding contextual windows, thus reducing memory footprint. We validate the approach on established spoken dialogue datasets and show that it can achieve state-of-the-art performance with much fewer trainable parameters. | |
Internacional
|
Si |
Nombre congreso
|
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) |
Tipo de participación
|
960 |
Lugar del congreso
|
|
Revisores
|
Si |
ISBN o ISSN
|
978-1-7281-0306-8 |
DOI
|
10.1109/ASRU46091.2019.9003735 |
Fecha inicio congreso
|
02/12/2019 |
Fecha fin congreso
|
03/12/2019 |
Desde la página
|
800 |
Hasta la página
|
806 |
Título de las actas
|
Actas del 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) |