Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

NAACL
2007

favoriteEmaildiscussreport

142views Computational Linguistics» more NAACL 2007»

Exploiting Event Semantics to Parse the Rhetorical Structure of Natural Language Text

13 years 5 months ago

Exploiting Event Semantics to Parse the Rhetorical Structure of Natural Language Text

Download nlp.cs.uic.edu

Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to exploit event semantics in order to build discourse parse trees (DPT) based on informational rhetorical relations. Our work employs an Inductive Logic Programming (ILP) based rhetorical relation classiﬁer, a Neural Network based discourse segmenter, a bottom-up sentence level discourse parser and a shift-reduce document level discourse parser.

Rajen Subba

Real-time Traffic

Computational Linguistics | Discourse | Discourse Parse Trees | Level Discourse Parser | NAACL 2007 |

claim paper

Related Content

» ADROIT Automatic Discourse Relation Organizer of Internetbased Text

» Choosing Rhetorical Structures to Plan Instructional Texts

» The Naproche Project Controlled Natural Language Proof Checking of Mathematical Texts

» Modeling Prosodic Structures in Linguistically Enriched Environments

» A Linguistic Resource for Semantic Parsing of Motion Events

» A Natural Language Interface for Information Retrieval on Semantic Web Documents

» Automatic Detection and Classification of Social Events

» A Comparison of Alternative Parse Tree Paths for Labeling Semantic Roles

» Using a Diathesis Model for Semantic Parsing

Post Info
More Details (n/a)

Added	30 Oct 2010
Updated	30 Oct 2010
Type	Conference
Year	2007
Where	NAACL
Authors	Rajen Subba

Comments (0)