Discourse Representation Structure Parsing for Chinese
This work addresses the problem of semantic parsing for Chinese, a language lacking labeled data, but it is incremental as it adapts existing methods to a new domain.
The paper tackled Chinese semantic parsing without labeled data by automatically collecting linearized meaning representations and proposing a test suite for fine-grained evaluation, finding that parsing difficulty is mainly due to adverbs and that direct training on Chinese data yields slightly better performance than using machine translation and an English parser.
Previous work has predominantly focused on monolingual English semantic parsing. We, instead, explore the feasibility of Chinese semantic parsing in the absence of labeled data for Chinese meaning representations. We describe the pipeline of automatically collecting the linearized Chinese meaning representation data for sequential-to sequential neural networks. We further propose a test suite designed explicitly for Chinese semantic parsing, which provides fine-grained evaluation for parsing performance, where we aim to study Chinese parsing difficulties. Our experimental results show that the difficulty of Chinese semantic parsing is mainly caused by adverbs. Realizing Chinese parsing through machine translation and an English parser yields slightly lower performance than training a model directly on Chinese data.