A Comparative Study of Embedding Models in Predicting the Compositionality of Multiword Expressions
In this paper, we perform a comparative evaluation of off-the-shelf embedding models over the task of compositionality prediction of multiword expressions(``MWEs''). Our experimental results suggest that character- and document-level models capture knowledge of MWE compositionality and are effective in modelling varying levels of compositionality, with the advantage over word-level models that they do not require token-level identification of MWEs in the training corpus.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalRepresentation LearningWord EmbeddingsSimilar Papers 제목 키워드 기반
A Word Embedding Approach to Predicting the Compositionality of Multiword Expressions
How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions
In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings…
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositional…
On the Compositionality Prediction of Noun Phrases using Poincar\'e Embeddings
The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositional…