Joint Learning Of Word And Label Embeddings For Sequence Labelling In Spoken Language Understanding

Abstract

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.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keywu2019joint

Related papers

• Exploiting Sentence And Context Representations In Deep Neural Models For Spoken Language Understanding (2016)0.00
• Sequential End-to-end Intent And Slot Label Classification And Localization (2021)3.58
• Hierarchical Pre-training For Sequence Labelling In Spoken Dialog (2020)0.00
• Tie Your Embeddings Down: Cross-modal Latent Spaces For End-to-end Spoken Language Understanding (2020)9.03
• Multi-domain Adversarial Learning For Slot Filling In Spoken Language Understanding (2017)0.00
• Label-dependencies Aware Recurrent Neural Networks (2017)2.26
• Token-level Sequence Labeling For Spoken Language Understanding Using Compositional End-to-end Models (2022)0.00
• Joint Online Spoken Language Understanding And Language Modeling With Recurrent Neural Networks (2016)13.28