Generating Natural Language From Logic Expressions With Structural Representation

• Published in: IEEE/ACM transactions on audio, speech, and language processing Vol. 31; pp. 1499 - 1510
• Main Authors: Wu, Xin, Cai, Yi, Lian, Zetao, Leung, Ho-fung, Wang, Tao
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Artificial neural networks; Coders; Cognition; Computational modeling; graph convolutional networks; Logic; logic expressions; Machine learning; Natural language; Natural language generation; Natural languages; Qualitative analysis; Representations; Semantics; Sentences; Task analysis; Training; Tree-LSTM
• ISSN: 2329-9290; 2329-9304
• DOI: 10.1109/TASLP.2023.3263784

Incorporating logic reasoning with deep neural networks (DNNs) is an important challenge in machine learning. In this article, we study the problem of converting logical expressions into natural language. In particular, given a sequential logic expression, the goal is to generate its corresponding natural sentence. Since the information in a logic expression often has a hierarchical structure, a sequence-to-sequence baseline struggles to capture the full dependencies between words, and hence it often generates incorrect sentences. To alleviate this problem, we propose a model to convert Structural Logic Expressions into Natural Language (SLEtoNL). SLEtoNL converts sequential logic expressions into structural representation and leverages structural encoders to capture the dependencies between nodes. The quantitative and qualitative analyses demonstrate that our proposed method outperforms the seq2seq model, which is based on the sequential representation, and outperforms strong pretrained language models (e.g., T5, BART, GPT3) with a large margin (28.6 in BLEU3) in out-of-distribution evaluation.