英文摘要 |
Machine Reading (MR) aims to make the knowledge contained in the text available in forms that machines can use them for automated processing. That is, machines will learn to read from a few examples and they will read to learn what they need in order to answer questions or perform some reasoning task. Since a domain-independent MR system is difficult to build, the Math Word Problem (MWP) is frequently chosen as the first test case to study MR. The main reason for that is that MWP not only has less complicated syntax but also requires less amount of domain knowledge. The architecture of our proposed approach is shown in Figure 1. First, every sentence in the MWP, including both body text and the question text, is analyzed by the Language Analysis module, which transforms each sentence into its corresponding semantic representation tree. The sequence of semantic representation trees is then sent to the Problem Resolution module, which adopts logic inference approach, to obtain the answer of each question in the MWP. Finally, the Explanation Generation (EG) module will explain how the answer is found (in natural language text) according to the given reasoning chain (which includes all related logic statements and inference steps to reach the answer). |