Coreference resolution is an important processing step for semantic analysis of a text in NLP. It facilitates in better understanding of the text. So coreference resolution tool becomes a necessity for every NLP process meant for text understanding or generation. The task of selecting a tool from a range of available open source coreference resolution tools can be challenging. This paper presents a study of these available open source coreference resolution tools with the aim to select a better performing tool that can be integrated into an NLP pipeline with ease. After the initial theoretical study of 13 open source coreference tools, a black box testing approach has been followed for testing the performance of 5 selected tools for their performance, usage and ease of integration for building an NLP application like summarization system, dialogue system etc. The performance evaluation is done using standard CoNLL 2012 coreference dataset for English language. The coreference marked output is evaluated against the manually tagged gold standard dataset. The performance is analyzed to select the best performing coreference tool for practical applications.

Coreference resolution, coreference tools, entity resolution, NLP

[1] R. Sukthanker, S. Poria, E. Cambria, R. Thirunavukarasu, “Anaphora and Coreference Resolution: A Review.” CoRR, abs/1805.11824, 2018.
[2] P. Elango, "Coreference resolution: A survey." University of Wisconsin, Madison, WI, 2005.
[3] J. Zheng, W. W. Chapman, R. S. Crowley, G. K. Savova, “Coreference resolution: A review of general methodologies and applications in the clinical domain”. Journal of biomedical informatics, 2011.
[4] B. Benatallah, S. Venugopal, S. H. Ryu, H. R. Motahari-Nezhad, W. Wang, “A systematic review and comparative analysis of cross-document coreference resolution methods and tools”. Computing, 1-37, 2016.
[5] B. O`Connor, M. Heilman, "ARKref: A rule-based coreference resolution system." arXiv preprint arXiv:1310.1975 , 2013.
[6] Y. Versley, S. P. Ponzetto, M. Poesio, V. Eidelman, A. Jern, J. Smith, A. Moschitti, “BART: A modular toolkit for coreference resolution.” In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies, 2008.
[7] D. Greg, D. L. Wright Hall, D. Klein. "Decentralized Entity-Level Modeling for Coreference Resolution." ACL, 2013.
[8] M. Dimitrov, K. Bontcheva, H. Cunningham, D. Maynard, "A Lightweight Approach to Coreference Resolution for Named Entities in Text”, Anaphora Processing: Linguistic, cognitive and computational modelling 263, 2005.
[9] M. Poesio, K. M. Alexandrov, "A General-Purpose, Off-the-shelf Anaphora Resolution Module: Implementation and Preliminary Evaluation." LREC, 2004.
[10] K. W. Chang, R. Samdani, A. Rozovskaya, M. Sammons, D. Roth, “Illinois-Coref: The UI system in the CoNLL-2012 shared task.” In Joint Conference on EMNLP and CoNLL-Shared Task (pp. 113-117). Association for Computational Linguistics, 2012.
[11] S. Lappin, J. L. Herbert, "An algorithm for pronominal anaphora resolution." Computational linguistics 20.4 (1994): 535-561, 1994.
[12] Q. Long, K. Min-Yen, C. Tat-Seng, “A Public Reference Implementation of the RAP Anaphora Resolution Algorithm.” In proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC 2004). Vol. I, pp. 291-294, 2004.
[13] V. Stoyanov, C. Cardie, N. Gilbert, E. Riloff, D. Buttler, D. Hysom, "Coreference Resolution with Reconcile", Proceedings of the Conference of the 48th Annual Meeting of the Association for Computational Linguistics, ACL, 2010.
[14] E. Sapena, L. Padro ́, J. Turmo, “RelaxCor: A Global Relaxation Labeling Approach to Coreference Resolution.” In Proceedings of the ACL Workshop on Semantic Evaluations (SemEval- 2010), Uppsala, Sweden, July, 2010.
[15] H. Lee, Y. Peirsman, A. Chang, N. Chambers, M. Surdeanu, D. Jurafsky, “Stanford`s multi-pass sieve coreference resolution system at the CoNLL-2011 shared task.” In Proceedings of the fifteenth conference on computational natural language learning: Shared task (pp. 28-34). Association for Computational Linguistics, 2011.
[16] K. Clark, C. D. Manning, “Deep reinforcement learning for mention-ranking coreference models. “ In Proceedings of the Conference of the Emperical Methods in Natural Language Processing, 2016.
[17] R. Agerri, J. Bermudez, G. Rigau, “IXA pipeline: Efficient and Ready to Use Multilingual NLP tools.” In LREC (Vol. 2014, pp. 3823-3828), 2014.
[18] M. Vilain, J. Burger, J. Aberdeen, D. Connolly, L. Hirschman, “A model-theoretic coreference scoring scheme.” In Proceedings of the 6th conference on Message understanding (pp. 45-52). Association for Computational Linguistics, 1995.
[19] A. Bagga, B. Baldwin, B., “Algorithms for scoring coreference chains.” In The first international conference on language resources and evaluation workshop on linguistics coreference (Vol. 1, pp. 563-566), 1998.
[20] X. Luo, “On coreference resolution performance metrics.” In Proceedings of the conference on human language technology and empirical methods in natural language processing (pp. 25-32). Association for Computational Linguistics, 2005.
[21] K. Raghunathan, H. Lee, S. Rangarajan, N. Chambers, M. Surdeanu, D. Jurafsky, C. Manning, “A multi-pass sieve for coreference resolution.” In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, 2010.
[22] A.H.N. Kishore, M. Saravanan, “An Extensive Evaluation of Anaphora Resolution Based Abstract Generation System.” International Journal on Computer Science and Engineering, 5(1), p.8, 2013.
[23] H.M. Alfawareh, S. Jusoh, “Resolving ambiguous entity through context knowledge and fuzzy approach. “International journal on computer science and engineering (IJCSE), 3(1), pp.410-422, 2011.