CIS Slot Filling System

Introduction

This page provides the source code and prepared ressources for the CIS slot filling system, as used in the entry to the 2015 shared task evaluations. It is described in [1] (pdf).

Resources

Code: cisSFsystem

For running the code, you need to have access to the TAC evaluation corpus and the query files from 2015.

Furthermore, the code uses external tools, such as Stanford CoreNLP [2], Terrier [3] and WAT [4] and applies a pattern matcher based on the distant supervised patterns from Relation Factory [5].

Cite

If you use the provided code in your work, please cite the following papers:

@article{adelSF2019,
  author = {Heike Adel and Hinrich Sch\"{u}tze},
  title = {Type-aware Convolutional Neural Networks for Slot Filling},
  journal = {accepted to appear in: Journal of Artificial Intelligence Research (JAIR)},
  year = {2019}
}

@inproceedings{adelSF2015,
  author = {Heike Adel and Hinrich Sch\"{u}tze},
  title = {CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling},
  booktitle = {Proceedings of Text Analysis Conference (TAC)},
  year = {2015}
}

References

[1] Heike Adel and Hinrich Schütze: "CIS at TAC Cold Start 2015: Neural Networks and Coreference Resolution for Slot Filling", TAC 2015.

[2] Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David McClosky: "The Stanford CoreNLP Natural Language Processing Toolkit", ACL System Demonstrations 2014.

[3] Iadh Ounis, Gianni Amati, Vassilis Plachouras, Ben He, Craig Macdonald and Christina Lioma: "Terrier: A High Performance and Scalable Information Retrieval Platform", SIGIR Workshop on Open Source Information Retrieval (OSIR) 2006.

[4] Francesco Piccinno and Paolo Ferragina: "From Tagme to WAT: A New Entity Annotator", First International Workshop on Entity Recognition and Disambiguation 2014.

[5] Benjamin Roth, Tassilo Barth, Grzegorz Chrupała, Martin Gropp and Dietrich Klakow: "RelationFactory: A Fast, Modular and Effective System for Knowledge Base Population", EACL System Demonstrations 2014.

Contact: Heike Adel (website)