Getting More Out Of Syntax with PropS
This addresses the need for better semantic parsing in NLP applications, but it appears incremental as it builds on existing dependency trees.
The paper tackles the problem of semantic NLP applications relying on dependency trees that often miss proposition structures, leading to ad-hoc post-processing or information loss, and presents PropS as a new output representation to explicitly express proposition structure from syntax with an associated extraction tool.
Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences. Yet, while much semantic structure is indeed expressed by syntax, many phenomena are not easily read out of dependency trees, often leading to further ad-hoc heuristic post-processing or to information loss. To directly address the needs of semantic applications, we present PropS -- an output representation designed to explicitly and uniformly express much of the proposition structure which is implied from syntax, and an associated tool for extracting it from dependency trees.