-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #33 from openeventdata/paper
Paper
- Loading branch information
Showing
2 changed files
with
73 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,26 @@ | ||
%% This BibTeX bibliography file was created using BibDesk. | ||
%% http://bibdesk.sourceforge.net/ | ||
%% Created for John Beieler at 2016-10-23 17:47:58 -0400 | ||
%% Saved with string encoding Unicode (UTF-8) | ||
@unpublished{tabari, | ||
Author = {Philip A. Schrodt}, | ||
Date-Added = {2016-10-23 21:47:51 +0000}, | ||
Date-Modified = {2016-10-23 21:47:55 +0000}, | ||
Note = {Paper presented at the International Studies Association, Chicago, 21-24 February 2001}, | ||
Title = {Automated Coding of International Event Data Using Sparse Parsing Techniques}, | ||
Year = {2001}} | ||
|
||
@unpublished{cameo, | ||
Author = {Deborah J. Gerner and Philip A. Schrodt and Omur Yilmaz and Rajaa Abu-Jabr}, | ||
Date-Added = {2016-10-23 21:47:14 +0000}, | ||
Date-Modified = {2016-10-23 21:47:14 +0000}, | ||
Note = {American Political Science Association, Boston, August 2002}, | ||
Title = {Conflict and Mediation Event Observations (CAMEO): A New Event Data Framework for the Analysis of Foreign Policy Interactions}, | ||
Year = {2001}} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,47 @@ | ||
--- | ||
title: 'PETRARCH2: Another Event Coding Program' | ||
tags: | ||
- event coding | ||
- natural language processing | ||
- computational linguistics | ||
authors: | ||
- name: Clayton Norris | ||
orcid: 0000-0001-5907-757X | ||
affiliation: 1 | ||
- name: Philip Schrodt | ||
orcid: 0000-0003-3495-4198 | ||
affiliation: 2 | ||
- name: John Beieler | ||
orcid: 0000-0001-7811-4399 | ||
affiliation: 3 | ||
affiliations: | ||
- name: University of Chicago | ||
index: 1 | ||
- name: Parus Analytics | ||
index: 2 | ||
- name: Human Language Technology Center of Excellence<br />Johns Hopkins University | ||
index: 3 | ||
date: 23 October 2016 | ||
bibliography: paper.bib | ||
--- | ||
|
||
# Summary | ||
|
||
The PETRARCH2 coding program implements a new coding algorithm, based on a | ||
syntactic constiuency parse, to extract who-did-what-to-whom political event data from | ||
structured news stories. Events are coded according to the CAMEO [@cameo] coding | ||
ontology. This software improves upon previous-generation coding software | ||
such as TABARI [@tabari] by using a deep syntactic parse rather than shallow | ||
parsing. | ||
|
||
At the level of assigning codes, PETRARCH2 is largely dictionary based, working from extensive | ||
dictionaries of verb phrases to identify the type of event, and noun phrases to | ||
identify both the actor (generally a proper noun such as the name of a country or | ||
leader) and agent (generally a common noun identifying a role such as "police" or | ||
"protesters"). These dictionaries incorporate the synonym sets from WordNet, are | ||
open source, and are included in the distribution. | ||
|
||
PETRARCH2 has primarily been run using Treebank output from the Stanford CoreNLP | ||
system. It can be integrated with other software on the https://github.com/openeventdata/ site | ||
to handle either continuous near-real-time coding or batch coding, as well as | ||
auxiliary programs for geolocation and simple deduplication. |