Dependencies

In this section we list the external libraries that are required in our Relationship Extraction Framework and the papers describing techniques that have been implemented.
External Libraries

  • Apache Ant : Version 1.8.2 and above (ant.jar)

  • Conja : Version 1.0.2 and above (conja-1.02.jar)

  • Google Data Java Client Library : Version 2.0 and above

  • GSon : Version 1.4 and above (gson-1.4.jar)

  • Guava : Version 7 and above (guava-r07.jar)

  • JDOM : Version 1.1.2 and above (jdom.jar)

  • JLibSVM : Version 2.88 and above (jlibsvm-0.902.jar)

  • JSon JDK : Version 2.4 and above (json-lib-2.4-jdk15.jar)

  • JSon Org : Version 2.4 and above (json-org.jar)

  • LingPipe : Version 4.1.0 and above (lingpipe-4.1.0.jar)

  • Log4J : Version 1.2.13 and above (log4j-1.2.13.jar)

  • Apache Lucene : Version 3.4.0 and above (lucene-core.3.4.0.jar)

  • OpenNLP Maximum Entropy Library : Version 3.0.1 and above (opennlp-maxent-3.0.1-incubating.jar) [See required models]

  • OpenNLP Tools : Version 1.5.1 and above (opennlp-tools-1.5.1.jar) [See required models]

  • ParallelColt : Version 0.9.4 and above (parallelcolt-0.9.4.jar)

  • ReVerb : Version 1.0 and above (reverb.jar)

  • Saxon SQL : Version 9.3 and above (saxon9-sql.jar)

  • Saxon Enterprise Edition : Version 9.3 and above (saxon9ee-qc.jar)

  • Saxon Enterprise Edition : Version 9.3 and above (saxon9ee.jar)

  • Stanford Parser : Version 1.6.9 and above (stanford-parser.jar)

  • Weka : Version 3.6.2 and above (weka.jar)

    		•
    Required OpenNLP Models

    The following are the required models to be used by the OpenNLP objects in our framework.
  • en-chunker.bin : Chunker trained on conll2000 shared task data.

  • en-pos-maxent.bin : Maxent Part of Speech Tagger model trained on conllx ddt data.

  • en-sent.bin : Sentence Detector trained on opennlp training data.

  • en-token.bin : Tokenizer Trained on opennlp training data.

    • Referenced Papers

    This section lists the papers that describe some of the techniques implemented in our framework. Please, refer to these in case further details are needed.

    PR-DualRank

    Searching Patterns for Relation Extraction over the Web: Rediscovering the Pattern-Relation Duality. Y. Fang and K. C.-C. Chang. In WSDM, pages 825-834, 2011.
    Subsequences Kernel

    Subsequence Kernels for Relation Extraction. Razvan Bunescu and Raymond J. Mooney. In Proceedings of the 19th Conference on Neural Information Processing Systems (NIPS), 2005.
    Shortest Path Kernel

    A Shortest Path Dependency Kernel for Relation Extraction. Razvan Bunescu and Raymond J. Mooney. In Proceedings of the Joint Conference on Human Language Technology / Empirical Methods in Natural Language Processing (HLT/EMNLP), 2005.
    Bag Of NGrams Kernel

    Exploiting Shallow Linguistic Information for Relation Extraction from Biomedical Literature. Claudio Giuliano and Alberto Lavelli and Lorenza Romano. In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2006), 2006.
    Open Information Extraction (ReVerb)

    Open Information Extraction: the Second Generation. Oren Etzioni, Anthony Fader, Janara Christensen, Stephen Soderland and Mausam. In International Joint Conference on Artificial Intelligence, 2011.