ARKref is a Noun Phrase Coreference System.

It is a Java implementation of a syntactically rich, rule-based within-document coreference system very similar to (the syntactic components of) Haghighi and Klein (2009). It is useful as a starting point for incorporating coreference into larger information extraction and natural language processing systems. For example, by tweaking the gazetteers, customzing mention identification, turning the syntactic rules into log-linear features, etc., it can be made useful for a variety of applications.

It was developed by Brendan O'Connor and Michael Heilman, students in Noah Smith's ARK research group.

Online Demo

Enter a few sentences of text in the box below (or click on an example) and then click "Resolve." The system will take a few seconds per sentence to respond.

A Few Examples to Try

• Because Bill had said he really wanted to talk to Susan, she called him.
• John bought himself a book. Bob knew that John bought himself a book. John knew that Bob bought him a book, too.
• On the one, hand the Calverts had the power to create manorial estates. On the other, they could only make laws with the consent of freemen (property holders). They found that in order to attract settlers -- and make a profit from their holdings -- they had to offer people farms, not just tenancy on manorial estates.

Downloading

Download a release: arkref-20110321.tgz

More information

We are working on a real tech report describing it, but in the meantime, a preliminary document is available with the code. Please first read:

Aria Haghighi and Dan Klein. Simple Coreference Resolution with Rich Syntactic and Semantic Features. EMNLP 2009.

Out of the box, it performs about as well as H&K's 2009 system on the development data set (we have not evaluated on the test dataset). Its F-score is slightly higher, and the precision/recall tradeoff is different. Note that there is no semantic compatibility subsystem ("+SEM-COMPAT") and that we use a supersense tagger (Ciaramita and Altun, EMNLP 2006) rather than a named entity recognizer.

It depends on having a phrase structure parser. We use the Stanford Parser and include it in the download. ARKref also makes heavy use of the Stanford Tregex library for implementation of syntactic rules.