Multi-level Gated Recurrent Neural Network for dialog act classification

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1970–1979, Osaka, Japan, December 11-17 2016. Multi-level Gated Recurrent Neural Network for Dialog Act Classification Wei Li Key Laboratory of Computational Linguistics, Peking University Bejing, China liweitj47@pku.edu.cn Yunfang Wu Key Laboratory of Computational Linguistics, Peking University Bejing, China wuyf@pku.edu.cn Abstract In this paper we focus on the problem of dialog act (DA) labelling. This problem has recently attracted a lot of attention as it is an important sub-part of an automatic dialog model, which is currently in great demand. Traditional methods tend to see this problem as a sequence labelling task and deal with it by applying classifiers with rich features. Most of the current neural network models still omit the sequential information in the conversation. Henceforth, we apply a novel multi-level gated recurrent neural network (GRNN) with non-textual information to predict the DA tag. Our model not only utilizes textual information, but also makes use of non-textual and contextual information. In comparison, our model has shown significant improvement over previous works on the Switchboard Dialog Act (SWDA) data by over 6%. 1 Introduction Dialog act labelling is one of the ways to find the shallow discourse structures of natural language con- versations. It represents the meaning or intention of each short sentence within a conversation by giving a tag to each sentence (Austin and Urmson, 1962; Searle, 1969). DA can be of help to many tasks, for example, the DA of the current sentence provides very important information for answer generation in an automatic question answering system. This converts a complex system into a classification problem, enabling many existing systems to fit in the problem. Traditional methods apply classifiers with rich human-crafted features to tag the sentences. One can view each sentence in the dialog as a separate one and label it accordingly, such as the work of (Silva et al., 2011), but this results in the loss of sequential information in the conversation context. Stolcke et al. (2000) used a segmented version of switchboard dialog act (SWDA) (Godfrey et al., 1992) with 43 tags based on the DAMSL labelling system , and proposed to use a hidden Markov model with rich features to predict the DA of each sentence. Although their model produces relatively good results, the feature construction and tuning consume too much human effort, and also make the adaptation between tasks difficult. Using the deep learning framework, researchers have developed various systems to deal with DA and related problems like sentiment analysis and sentence classification. One can build a simple CNN architecture like Kim (2014) to do the labelling work. However, the sentences in a conversation are highly variant in length, some of which can be as short as one to two words or may even include nothing but some telephone script symbols. For example, a lot of sentences consist of nothing but ”<laughter>.” and ”Okay”. To be specific, in the SWDA data, 3,253 sentences consist of a single word and the …

Content truncated to 500 words