VectorWeavers at SemEval-2016 Task 10: From Incremental Meaning to Semantic Unit (phrase by phrase)

Published:

Andrei Shcherbakov, Ekaterina Vylomova, Fei Liu and Timothy Baldwin (2016) VectorWeavers at SemEval-2016 Task 10: From Incremental Meaning to Semantic Unit (phrase by phrase), In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, USA, pp. 946-952.

@InProceedings{Scherbakov+:2016,
  author = 	{Scherbakov, Andreas and Vylomova, Ekaterina and Liu, Fei and Baldwin, Timothy},
  title = 	{VectorWeavers at SemEval-2016 Task 10: From Incremental Meaning to Semantic Unit (phrase by phrase)},
  booktitle = {Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)},
  year = 	{2016},
  address = {San Diego, USA},
  pages = 	{946--952}
}

Abstract

This paper describes an experimental approach to Detection of Minimal Semantic Units and their Meaning (DiMSUM), explored within the framework of SemEval’16 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.