In this paper we propose to use text chunking for controlling a bottom-up parser. As it is well known, during analysis such parsers produce many constituents not contributing to the nal solution(s). Most of these constituents are introduced due to the parser inability of checking the input context around them. Preliminary text chunking allows to focus directly on the constituents that seem more likely and to prune the search space in the case some satisfactory solutions are found. Preliminary experiments show that a CYK-like parser controlled through chunking is deenitely more eecient than a traditional parser without signiicantly losing in correctness. Moreover the quality of possible partial results produced by the controlled parser is high. The strategy is particularly suited for tasks like Information Extraction from text (IE) where sentences are often long and complex and it is very diicult to have a complete coverage. Hence, there is a strong necessity of focusing on the most likely solutions; furthermore, in IE the quality of partial results is important.
[1]
David D. McDonald,et al.
Robust partial-parsing through incremental, multi-algorithm processing
,
1992
.
[2]
Bob Carpenter,et al.
The logic of typed feature structures
,
1992
.
[3]
David S. Day,et al.
Finite-state phrase parsing by rule sequences
,
1996,
COLING.
[4]
Mats Wirén,et al.
A Comparison of Rule-Invocation Strategies in Context-Free Chart Parsing
,
1987,
EACL.
[5]
Steven Abney,et al.
Parsing By Chunks
,
1991
.
[6]
Douglas E. Appelt,et al.
FASTUS: A Finite-state Processor for Information Extraction from Real-world Text
,
1993,
IJCAI.
[7]
Douglas E. Appelt,et al.
Robust Processing of Real-World Natural-Language Texts
,
1992,
ANLP.
[8]
W. Lehnert.
Cognition, Computers, and Car Bombs: How Yale Prepared Me for the 90's
,
2013
.