Accession Number:

ADA587620

Title:

NavyTime: Event and Time Ordering from Raw Text

Descriptive Note:

Conference paper

Corporate Author:

NAVAL ACADEMY ANNAPOLIS MD

Personal Author(s):

• Chambers, Nathanael

Report Date:

2013-06-01

Pagination or Media Count:

6.0

Abstract:

This paper describes a complete eventtime ordering system that annotates raw text with events, times, and the ordering relations between them at the SemEval-2013 Task 1. Task 1 is a unique challenge because it starts from raw text, rather than pre-annotated text with known events and times. A working system first identifies events and times, then identifies which events and times should be ordered, and finally labels the ordering relation between them. We present a split classifier approach that breaks the ordering tasks into smaller decision points. Experiments show that more specialized classifiers perform better than few joint classifiers. The NavyTime system ranked second both overall and in most subtasks like event extraction and relation labeling.

Descriptors:

• *CLASSIFICATION
• *TEXT PROCESSING
• DATA MINING
• DECISION MAKING
• EXTRACTION
• LABELS
• TIME

Subject Categories:

• Information Science
• Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE