Constituent Parsing as Sequence Labeling release_d5nlvhcsazbszhurr5hssmwn7u

by Carlos Gómez-Rodríguez, David Vilares

Released as a article .

2019  

Abstract

We introduce a method to reduce constituent parsing to sequence labeling. For each word w_t, it generates a label that encodes: (1) the number of ancestors in the tree that the words w_t and w_t+1 have in common, and (2) the nonterminal symbol at the lowest common ancestor. We first prove that the proposed encoding function is injective for any tree without unary branches. In practice, the approach is made extensible to all constituency trees by collapsing unary branches. We then use the PTB and CTB treebanks as testbeds and propose a set of fast baselines. We achieve 90.7 set, outperforming the Vinyals et al. (2015) sequence-to-sequence parser. In addition, sacrificing some accuracy, our approach achieves the fastest constituent parsing speeds reported to date on PTB by a wide margin.
In text/plain format

Archived Files and Locations

application/pdf  437.1 kB
file_fkdtt3ykubcezoj35twhx2ehvi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-09-17
Version   v2
Language   en ?
arXiv  1810.08994v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 97ce3c34-b1ad-451c-9280-fcf4c68987cb
API URL: JSON