PP Attachment: Where do We Stand?

Daniël de Kok, Jianqiang Ma, Corina Dima, Erhard Hinrichs


Abstract
Prepostitional phrase (PP) attachment is a well known challenge to parsing. In this paper, we combine the insights of different works, namely: (1) treating PP attachment as a classification task with an arbitrary number of attachment candidates; (2) using auxiliary distributions to augment the data beyond the hand-annotated training set; (3) using topological fields to get information about the distribution of PP attachment throughout clauses and (4) using state-of-the-art techniques such as word embeddings and neural networks. We show that jointly using these techniques leads to substantial improvements. We also conduct a qualitative analysis to gauge where the ceiling of the task is in a realistic setup.
Anthology ID:
E17-2050
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
311–317
Language:
URL:
https://aclanthology.org/E17-2050
DOI:
Bibkey:
Cite (ACL):
Daniël de Kok, Jianqiang Ma, Corina Dima, and Erhard Hinrichs. 2017. PP Attachment: Where do We Stand?. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 311–317, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
PP Attachment: Where do We Stand? (de Kok et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-2050.pdf