Joint learning of word and label embeddings for sequence labelling in spoken language understanding
| Autor: | Nancy F. Chen, Jiewen Wu, Pavitra Krishnaswamy, Luis Fernando D'Haro, Rafael E. Banchs |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence Association (object-oriented programming) computer.software_genre Machine Learning (cs.LG) 030507 speech-language pathology & audiology 03 medical and health sciences Sequence Telecomunicaciones Computer Science - Computation and Language business.industry Range (mathematics) Recurrent neural network Artificial Intelligence (cs.AI) Memory footprint Artificial intelligence Distributional semantics 0305 other medical science business computer Computation and Language (cs.CL) Natural language processing Word (computer architecture) Spoken language |
| Zdroj: | 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | Actas del 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) | 14/12/2019-18/12/2019 | Singapore ASRU Archivo Digital UPM Universidad Politécnica de Madrid |
| Popis: | 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-of-the-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. Accepted for publication at ASRU 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|