Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Chunking and Dependency Parsing Giuseppe Attardi, Felice Dell'Orletta

Summary: Chunking and Dependency Parsing
Giuseppe Attardi, Felice Dell'Orletta
Affiliation1, Affiliation2, Affiliation3
Address1, Address2, Address3
author1@xxx.yy, author2@zzz.edu, author3@hhh.com
Since chunking can be performed efficiently and accurately, it is attractive to use it as a preprocessing step in full parsing stages. We
analyze whether providing chunk data to a statistical dependency parser can benefit its accuracy. We present a set of experiments meant
to select first a set of features that provide the greates improvement to a Shift/Reduce dependency parser, then to determine an appropriate
feature model. We report on accuracy gain obtained using features from chunks produced using a statistical chunker as well as from an
approximate representation of noun phrases induced directly by the parser. Finally we analyze the degree of accuracy that such a parser
can achieve in chunking compared to a specialized statistical chunker.
1. Introduction
Chunking or shallow parsing segments a sentence into a se-
quence of syntactic constituents or chunks, i.e. sequences
of adjacent words grouped on the basis of linguistic prop-
erties (Abney, 1996).
This process can be carried out efficiently and thus chunk-
ing can be useful in several tasks, for instance Termi-
nology Discovery, Named Entity Recognition (Carreras &


Source: Attardi, Giuseppe - Dipartimento di Informatica, UniversitÓ di Pisa


Collections: Computer Technologies and Information Sciences