Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
This work addresses dialogue interpretation for natural language processing applications, but it is incremental as it builds on existing dynamic memory networks with adversarial training.
The authors tackled the problem of dialogue act classification by formulating it as a question-answering task and using an improved dynamic memory network with hierarchical pyramidal utterance encoder and adversarial training. The model achieved better performance and robustness compared to state-of-the-art baselines on the Switchboard and MapTask datasets.
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.