Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
Autor: | Chen Liu, Chenyu Yang, Ruisheng Cao, Lu Chen, Rao Ma, Kai Yu, Su Zhu, Yanbin Zhao |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Process (engineering) Computer science 010501 environmental sciences computer.software_genre 01 natural sciences Paraphrase Machine Learning (cs.LG) Annotation 0502 economics and business 050207 economics 0105 earth and related environmental sciences Parsing Computer Science - Computation and Language business.industry 05 social sciences DUAL (cognitive architecture) Logical form Artificial intelligence business Computation and Language (cs.CL) computer Natural language Utterance Natural language processing |
Zdroj: | ACL |
Popis: | One daunting problem for semantic parsing is the scarcity of annotation. Aiming to reduce nontrivial human labor, we propose a two-stage semantic parsing framework, where the first stage utilizes an unsupervised paraphrase model to convert an unlabeled natural language utterance into the canonical utterance. The downstream naive semantic parser accepts the intermediate output and returns the target logical form. Furthermore, the entire training process is split into two phases: pre-training and cycle learning. Three tailored self-supervised tasks are introduced throughout training to activate the unsupervised paraphrase model. Experimental results on benchmarks Overnight and GeoGranno demonstrate that our framework is effective and compatible with supervised training. accepted by ACL 2020 Long, 12 pages, 5 figures |
Databáze: | OpenAIRE |
Externí odkaz: |