Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment
Name
tacl_a_00203.pdf
Description
Published version
Size
352.98 KB
Format
Adobe PDF
Checksum (MD5)
031aa56e029871b262e17bd9d85b96cc
Author(s)
Belinkov, Yonatan
Lei, Tao
Barzilay, Regina
Globerson, Amir
Date Issued
2014
Journal
Transactions of the Association for Computational Linguistics
Publisher
MIT Press - Journals
Version
Final published version
Abstract
Prepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. However, state-of-the-art systems that employ such representations yield modest gains in PP attachment accuracy. In this paper, we show that word vector representations can yield significant PP attachment performance gains. This is achieved via a non-linear architecture that is discriminatively trained to maximize PP attachment accuracy. The architecture is initialized with word vectors trained from unlabeled data, and relearns those to maximize attachment accuracy. We obtain additional performance gains with alternative representations such as dependency-based word vectors. When tested on both English and Arabic datasets, our method outperforms both a strong SVM classifier and state-of-the-art parsers. For instance, we achieve 82.6% PP attachment accuracy on Arabic, while the Turbo and Charniak self-trained parsers obtain 76.7% and 80.8% respectively.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1162/TACL_A_00203
