Towards Causal Explanation Detection with Pyramid Salient-Aware Network

Towards Causal Explanation Detection with Pyramid Salient-Aware Network Xinyu Zuo1,2, Yubo Chen1,2, Kang Liu1,2, Jun Zhao1,2 1National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China {xinyu.zuo,yubo.chen,kliu,jzhao}@nlpr.ia.ac.cn Abstract Causal explanation analysis (CEA) can assist us to understand the reasons behind daily events, which has been found very helpful for understanding the coherence of messages. In this paper, we focus on Causal Explanation Detection, an important subtask of causal explanation analysis, which determines whether a causal explanation exists in one message. We design a Pyramid Salient-Aware Network (PSAN) to detect causal explanations on messages. PSAN can assist in causal explanation detection via capturing the salient semantics of discourses contained in their keywords with a bottom graph-based word-level salient network. Furthermore, PSAN can modify the dominance of discourses via a top attention-based discourse-level salient network to enhance explanatory semantics of messages. The experiments on the commonly used dataset of CEA shows that the PSAN outperforms the state-of-the-art method by 1.8% F1 value on the Causal Explanation Detection task. 1 Introduction Causal explanation detection (CED) aims to detect whether there is a causal explanation in a given message (e.g. a group of sentences). Linguistically, there are coherence relations in messages which explain how the meaning of different textual units can combine to jointly build a discourse meaning for the larger unit. The explanation is an important relation of coherence which refers to the textual unit (e.g. discourse) in a message that expresses explanatory coherent semantics (Jurafsky, 2010). As shown in Figure 1, M1 can be divided into three discourses, and D2 is the explanation that expresses the reason why it is advantageous for the equipment to operate at these temperatures. CED is important for tasks that require an understanding of textual expression (Son et al., 2018). For example, for question answering, the answers of questions are most likely to be in a group of sentences that contains causal explanations (Oh et al., 2013). Furthermore, the summarization of event descriptions can be improved by selecting causally motivated sentences (Hidey and McKeown, 2016). Therefore, CED is a problem worthy of further study. The existing methods mostly regard this task as a classification problem (Son et al., 2018). At present, there are mainly two kinds of methods, feature-based methods and neural-based methods, for similar semantic understanding tasks in discourse granularity, such as opinion sentiment classification and dis- course parsing (Nejat et al., 2017; Jia et al., 2018; Soricut and Marcu, 2003). The feature-based methods can extract the feature of the relation between discourses. However, these methods do not deal well with the implicit instances which lack explicit features. For CED, as shown in Figure 1, D2 lacks explicit features such as because of, due to, or the features of tenses, which are not friendly for feature-based methods. The methods based on neural network are mainly Tree-LSTM model (Wang et al., 2017) and hierarchical Bi-LSTM model (Son et al., …

Content truncated to 500 words