Search Results for author:
Found 8 papers, 0 papers with code
Without lexicons, multiword expression identification will never fly: A position statement
Because most multiword expressions (MWEs), especially verbal ones, are semantically non-compositional, their automatic identification in running text is a prerequisite for semantically-oriented downstream applications.
Unsupervised Compositionality Prediction of Nominal Compounds
General crosslingual analyses reveal the impact of morphological variation and corpus size in the ability of the model to predict compositionality, and of a uniform combination of the components for best results.
The PARSEME Shared Task on Automatic Identification of Verbal Multiword Expressions
This paper presents the corpus annotation methodology and outcome, the shared task organisation and the results of the participating systems.
mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic MWE Processing
This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings.
