文献类型：期刊文献

英文题名：Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning

作者：Lu, Xuantao[1]; Liu, Jingping[2,3]; Gu, Zhouhong[1]; Tong, Hanwen[1]; Xie, Chenhao[2]; Huang, Junyang[1]; Xiao, Yanghua[1,2,4]; Wang, Wenguang[5]

机构：[1] Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China; [2] SenseDeal Intelligent Technology Co., Ltd., Beijing, China; [3] School of Information Science and Engineering, East China University of Science and Technology, China; [4] Fudan-Aishu Cognitive Intelligence Joint Research Center, China; [5] DataGrand Inc., Shanghai, China

年份：2022

卷号：29

期号：1

起止页码：5419

外文期刊名：Proceedings - International Conference on Computational Linguistics, COLING

收录：EI(收录号：20233014453030)

语种：英文

外文关键词：Computational linguistics - Computer circuits - Formal logic - Learning systems - Natural language processing systems - Semantics

摘要：Semantic parsing converts natural language utterances into structured logical expressions. We consider two such formal representations: Propositional Logic (PL) and First-order Logic (FOL). The paucity of labeled data is a major challenge in this field. In previous works, dual reinforcement learning has been proposed as an approach to reduce dependence on labeled data. However, this method has the following limitations: 1) The reward needs to be set manually and is not applicable to all kinds of logical expressions. 2) The training process easily collapses when models are trained with only the reward from dual reinforcement learning. In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process. In addition to the technical contribution, a Chinese-PL/FOL dataset is constructed to compensate for the paucity of labeled data in this field. Experimental results show that the proposed method outperforms competitors on several datasets. Furthermore, by introducing PL/FOL generated by our model, the performance of existing Natural Language Inference (NLI) models is further enhanced. ? 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.