• Aucun résultat trouvé

Erratum: “Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment”

N/A
N/A
Protected

Academic year: 2022

Partager "Erratum: “Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment”"

Copied!
2
0
0

Texte intégral

(1)

Erratum: “Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment”

Yonatan Belinkov, Tao Lei, Regina Barzilay, Amir Globerson

Abstract

Correction for the list of authors in the refer- ence (Seddah et al., 2013).

Correction for the list of authors in the refer- ence (Seddah et al., 2013).

References

Djam´e Seddah, Reut Tsarfaty, Sandra K¨ubler, Marie Can- dito, Jinho D. Choi, Rich´ard Farkas, Jennifer Fos- ter, Iakes Goenaga, Koldo Gojenola Galletebeitia, Yoav Goldberg, Spence Green, Nizar Habash, Marco Kuhlmann, Wolfgang Maier, Joakim Nivre, Adam Przepi´orkowski, Ryan Roth, Wolfgang Seeker, Yan- nick Versley, Veronika Vincze, Marcin Woli´nski, Alina Wr´oblewska, and Eric Villemonte de la Clergerie.

2013. Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologi- cally Rich Languages. InProceedings of SPMRL.

101

Transactions of the Association for Computational Linguistics, vol. 3, pp. 101–101, 2015.

Published 2/2015. c2015 Association for Computational Linguistics.

(2)

102

Références

Documents relatifs

7.1 Details of inducing word representations The Brown clusters took roughly 3 days to induce, when we induced 1000 clusters, the baseline in prior work (Koo et al., 2008; Ratinov

[r]

To cope with the variety of information type and struc- ture and with the amount of available data, links between the reality of space regions and abstract data, inherent to map

[r]

While generating the prepositional phrase corpus used in this study we paid special at- tention to derivative prepositions and functional phrases containing prepositions.. We

We calculate the vectors on 300K actual job postings on the Careerbuilder Website, using 6 different models (FastText, Word2Vec, Glove-6B-300 , Glove- 840B-300 [2,10,13], and

Having a pre-trained biLM (Bidirectional Language Model) with the architecture described above and a certain algorithm for solving the target problem of NLP it is sufficiently easy

This empirical study of a complex group of patients with multiple chronic concurrent conditions (diabetes, cardiovascular and kidney diseases) explores the use