Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
31 citations recorded by the source corpus.
The goal of this paper is to learn cross-domain representations for slot filling task in spoken language understanding (SLU). Most of the recently published SLU models are domain-specific ones that work on individual task domains. Annotating data for each individual task domain is both financially costly and non-scalable. In this work, we propose an adversarial training method in learning common features and representations that can be shared across multiple domains. Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain. In our experiments using data sets from multiple domains, we show that adversarial training helps in learning better domain-general SLU models, leading to improved slot filling F1 scores. We further show that applying adversarial learning on domain-general model also helps in achieving higher slot filling performance when the model is jointly optimized with domain-specific models.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ting-Wei Liu
- Wanxiang Che
- Young-Bum Kim
- Srinivasan Parthasarathy
- Nikhita Vedula
- Nedim Lipka
- Pranav Maneriker
- Dongchan Kim
In Computer Vision and Pattern Recognition
- Young-Bum Kim
- Wanxiang Che
- Srinivasan Parthasarathy
- Ruhi Sarikaya
- Dongchan Kim
- Ting-Wei Liu
- Yue Zhang
Citations in the corpus
- Towards Open Intent Discovery for Conversational Text (2019, background): “, to discover features and structures that are common across multiple domains [9, 25, 32].”
- Efficient Large-Scale Domain Classification with Personalized Attention (2018, background): “…learning (El-Kahky et al., 2014; Kim et al., 2015a,c; Chen et al., 2016a; Yang et al., 2017), domain adaptation (Kim et al., 2016; Jaech et al., 2016; Liu and Lane, 2017; Kim et al., 2017d,c) and contextual signals (Bhar-gava et al., 2013; Chen et al., 2016b; Hori et al., 2016; Kim et al., 2017a).”
- Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020, background): “Liu and Lane (2017) applies a shared-private LSTM to generate shared and domain-specific features.”