An Incremental Parser for Abstract Meaning Representation
This work addresses the need for efficient and accurate semantic parsing for natural language processing tasks, but it is incremental as it builds on existing AMR parsing methods.
The authors tackled the problem of parsing sentences into Abstract Meaning Representation (AMR) by developing a transition-based parser that operates in linear time, achieving competitive state-of-the-art performance on the LDC2015E86 dataset and outperforming others in named entity recovery and polarity handling.
Meaning Representation (AMR) is a semantic representation for natural language that embeds annotations related to traditional tasks such as named entity recognition, semantic role labeling, word sense disambiguation and co-reference resolution. We describe a transition-based parser for AMR that parses sentences left-to-right, in linear time. We further propose a test-suite that assesses specific subtasks that are helpful in comparing AMR parsers, and show that our parser is competitive with the state of the art on the LDC2015E86 dataset and that it outperforms state-of-the-art parsers for recovering named entities and handling polarity.