Coupled Representation Learning for Domains, Intents and Slots in Spoken Language Understanding
Authors:
- 1 December 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 714-719
Abstract
Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Language Understanding system. Our proposed model learns the vector representation of intents based on the slots tied to these intents by aggregating the representations of the slots. Similarly, the vector representation of a domain is learned by aggregating the representations of the intents tied to a specific domain. To the best of our knowledge, it is the first approach to jointly learning the representations of domains, intents, and slots using their hierarchical relationships. The experimental results demonstrate the effectiveness of the representations learned by our model, as evidenced by improved performance on the contextual cross-domain reranking task.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Intent detection using semantically enriched word embeddings2017
- The Technology Behind Personal Digital Assistants: An overview of the system architecture and key componentsIEEE Signal Processing Magazine, 2017
- Domain Attention with an Ensemble of Experts2017
- Word Embedding based Generalized Language Model for Information Retrieval2015
- Weakly Supervised Slot Tagging with Partially Labeled Sequences from Web Search Click Logs2015
- New Transfer Learning Techniques for Disparate Label Sets2015
- Using Recurrent Neural Networks for Slot Filling in Spoken Language UnderstandingIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Glove: Global Vectors for Word Representation2014
- Convolutional neural network based triangular CRF for joint intent detection and slot filling2013
- Machine learning in automated text categorizationACM Computing Surveys, 2002