About the Project

Summary

The ACL Network was originally created by Mark Thomas Joseph and is currently being maintained by Bryan Gibson under the supervision of Professor Dragomir R. Radev.

Acknowledgements

A number of students from the University of Michigan's CLAIR Group helped with the work involved to create the data, network, and webpages. We would like to thank:

This work has been partially supported by the National Science Foundation grant "Collaborative Research: BlogoCenter - Infrastructure for Collecting, Mining and Accessing Blogs", jointly awarded to UCLA and UMich as IIS 0534323 to UMich and IIS 0534784 to UCLA and by the National Science Foundation grant "iOPENER: A Flexible Framework to Support Rapid Learning in Unfamiliar Research Domains", jointly awarded to UMd and UMich as IIS 0705832.

About the Data

The ACL Anthology Network was built from the original pdf files available from the ACL Anthology. Using open source OCR technologies, in-house clean-up scripts, and often tedious manual labor, a web interface was developed that allowed for the annotation of individual references from each paper. A team of student research assistants manually matched references to existing ACL ID's returned using a keyword matching algorithm. Those citations deemed to refer to ACL papers but which were not automatically matched were marked for post-processing.

Publications using the AAN data

Using the Data

To use this data, please follow the following guidlines:

  1. For research only.
  2. Do not re-distribute.
  3. If you publish using this work, you should acknowledge its creators. Please use the following bibtex: 
    @techreport{Joseph&Radev07,
  author = "Joseph, Mark T. and Radev, Dragomir R.",
  title = "Citation Analysis, Centrality, and the ACL Anthology",
  institution = "University of Michigan. Department of Electrical Engineering and Computer Science",
  pdf = "http://tangra.si.umich.edu/\~radev/papers/csetr535-07.pdf",
  postscript = "http://tangra.si.umich.edu/\~radev/papers/csetr535-07.ps",
  papernum = "112",
  year =  "2007",
  number = "CSE-TR-535-07",
  x-category = "CLAIR,RADEV,MISC"
}
  4. Please inform us if you publish as we are interested in the output of this work.

A Note About the PageRank Centrality

Because of the nature of PageRank values, we have adjusted the results to make them more human readable. The actual value of any PageRank on this website can be found by dividing the numbers given by 1,000,000. We also truncate the decimal points, leaving instead only the integer value. So, for example, if a paper has a computed PageRank of 0.003456789, We would print that PageRank as 3456 after dropping the .789.

Future Plans

We are currently working on completing full-search capabilities. Currently, the search tool can only search for ACL ID's and link to the page for that individual paper. We hope to soon return results based on title and author search as well.

We are also currently in the middle of post-processing. Statistics will continue to be adjusted as the network is cleaned and expanded. Also, upon completion, we hope to have full network statistics available on the website.

Contact

If you have any questions regarding this website or its contents, or have comments, misspellings, or other general mistakes to report, please fill out the form on our Contact Us page.

Copyright © Univ. of Mich. and the CLAIR Group at the Univ. of Mich.
All information provided herein should be considered tentative and still under construction. Further analysis and correction is still being performed. Please remember that all statistics contained herein are the results of independent research and should not be considered a statement of fact regarding any of the papers, authors, or other entities they refer to.