Semantic reranking of CRF label sequences for verbal multiword expression identification - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2018

Semantic reranking of CRF label sequences for verbal multiword expression identification

Résumé

Verbal multiword Expressions (VMWE) identification can be addressed successfully as a sequence labelling problem via conditional random fields (CRFs) by returning the one label sequence with maximal probability. This work describes a system that reranks the top 10 most likely CRF candidate VMWE sequences using a decision tree regression model. The reranker aims to operationalise the intuition that a non-compositional MWE can have a different distributional behaviour than that of its constituent words. This is why it uses semantic features based on comparing the context vector of a candidate expression against those of its constituent words. However, not all VMWE are non-compostional, and analysis shows that non-semantic features also play an important role in the behaviour of the reranker. In fact, the analysis shows that the combination of the sequential approach of the CRF component with the context-based approach of the reranker is the main factor of improvement: our reranker achieves a 12% macro-average F1-score improvement on the basic CRF method, as measured using data from PARSEME shared task on VMWE identification.
Fichier principal
Vignette du fichier
PMWE2-semantic-reranking.pdf (657.67 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01930987 , version 1 (03-12-2018)

Identifiants

Citer

Erwan Moreau, Ashjan Alsulaimani, Alfredo Maldonado, Lifeng Han, Carl Vogel, et al.. Semantic reranking of CRF label sequences for verbal multiword expression identification. Multiword expressions at length and in depth: Extended papers from the MWE 2017 workshop, pp.177 - 207, 2018, ⟨10.5281/zenodo.1469559⟩. ⟨hal-01930987⟩
34 Consultations
70 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More