Su, S.-Y.S.-Y.SuHuang, C.-W.C.-W.HuangYUN-NUNG CHEN2021-05-052021-05-052020https://scholars.lib.ntu.edu.tw/handle/123456789/559425https://www.scopus.com/inward/record.uri?eid=2-s2.0-85070070917&partnerID=40&md5=8d00cb15c4359082ff8c81e4379be402Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP and dialogue fields. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural language generation is opposite, of which the goal is to construct corresponding sentences based on the given semantics. However, such dual relationship has not been investigated in literature. This paper proposes a novel learning framework for natural language understanding and generation on top of dual supervised learning, providing a way to exploit the duality. The preliminary experiments show that the proposed approach boosts the performance for both tasks, demonstrating the effectiveness of the dual relationship.1. © 2019 Association for Computational LinguisticsComputational linguistics; Semantics; Supervised learning; Critical researches; Learning frameworks; Natural language generation; Natural language understanding; Natural language processing systemsconference paper2-s2.0-85070070917