Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing
This work addresses semantic parsing for NLP applications like summarization and question answering, but it appears incremental as it builds on existing UCCA approaches.
The paper tackles the problem of semantic parsing using UCCA graph-based representation by proposing a novel self-attentive neural parsing model, achieving results for single-lingual and cross-lingual tasks with zero-shot and few-shot learning for low-resource languages.
Semantic parsing provides a way to extract the semantic structure of a text that could be understood by machines. It is utilized in various NLP applications that require text comprehension such as summarization and question answering. Graph-based representation is one of the semantic representation approaches to express the semantic structure of a text. Such representations generate expressive and adequate graph-based target structures. In this paper, we focus primarily on UCCA graph-based semantic representation. The paper not only presents the existing approaches proposed for UCCA representation, but also proposes a novel self-attentive neural parsing model for the UCCA representation. We present the results for both single-lingual and cross-lingual tasks using zero-shot and few-shot learning for low-resource languages.