From Incremental Meaning to Semantic Unit (phrase by phrase)
This work addresses a specific natural language processing problem for researchers in computational linguistics, but it appears incremental as it builds on existing methods like word embeddings and parser features.
The paper tackled the problem of detecting minimal semantic units and their meanings in multiword expressions by developing the DiMSUM approach using word embeddings and parser-based features with unidirectional incremental computation. The result was a system evaluated in SemEval 2016 Task 10, though no concrete performance numbers are provided in the abstract.
This paper describes an experimental approach to Detection of Minimal Semantic Units and their Meaning (DiMSUM), explored within the framework of SemEval 2016 Task 10. The approach is primarily based on a combination of word embeddings and parserbased features, and employs unidirectional incremental computation of compositional embeddings for multiword expressions.