Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
arXiv:1811.05021
Abstract
Dialogue Act (DA) classification is a challenging problem in dialogue interpretation, which aims to attach semantic labels to utterances and characterize the speaker's intention. Currently, many existing approaches formulate the DA classification problem ranging from multi-classification to structured prediction, which suffer from two limitations: a) these methods are either handcrafted feature-based or have limited memories. b) adversarial examples can't be correctly classified by traditional training methods. To address these issues, in this paper we first cast the problem into a question and answering problem and proposed an improved dynamic memory networks with hierarchical pyramidal utterance encoder. Moreover, we apply adversarial training to train our proposed model. We evaluate our model on two public datasets, i.e., Switchboard dialogue act corpus and the MapTask corpus. Extensive experiments show that our proposed model is not only robust, but also achieves better performance when compared with some state-of-the-art baselines.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Ensemble Adversarial Training: Attacks and Defenses
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
- Image Captioning with Semantic Attention
- Adversarial Training Methods for Semi-Supervised Text Classification
- Recurrent Convolutional Neural Networks for Discourse Compositionality
- Data Noising as Smoothing in Neural Network Language Models
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- Towards Neural Network-based Reasoning
- Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud