Mention Coreference Resolution Algorithm

A Mention Coreference Resolution Algorithm is a coreference resolution algorithm that can solve an Entity Mention Coreference Resolution Task and be implemented into an Entity Mention Coreference Resolution System.

• AKA: Coreference Resolver, Coreference Resolution Algorithm, Noun Phrase Coreference Resolution Algorithm.
• Context:
  • It can be applied by a Coreference Resolution System.
  • It can be:
    • a Supervised Entity Mention Coreference Resolution Algorithm.
    • an Unsupervised Mention Coreference Resolution Algorithm.
  • It can be a Pairwise Comparison Coreference Resolution Algorithm.
  • It can be an Anaphora Resolution Algorithm if the task is restricted to the Anaphora Resolution Task.
  • …
• Counter-Example(s):
  • a Data Record Coreference Resolution Algorithm.
• See: Entity Mention, Anaphora Resolution Algorithm.

---

---

References

2008

• (Clark and González-Brenes, 2008) ⇒ Jonathan H. Clark, and José P. González-Brenes. (2008). “Coreference: Current Trends and Future Directions." CMU course on Language and Statistics II Literature Review, Fall 2008.
  • QUOTE: Until recently, statistical approaches treated coreference resolution as a binary classification problem, in which the probability of two mentions from the text [math]\displaystyle{ i }[/math] and [math]\displaystyle{ j }[/math] having a coreferential outcome can be calculated from data by estimating the probability of Denis and Baldridge (2007). Pc(COREF|< i,j>) (1)
• (Finkel & Manning, 2008) ⇒ Jenny Rose Finkel, and Christopher D. Manning}. (2008). “Enforcing Transitivity in Coreference Resolution.” In: Proceedings of ACL-08: HLT, Short Papers.

2007

• (Ng, 2007) ⇒ Vincent Ng. (2007). “Semantic Class Induction And Coreference Resolution.” In: Proceedings of ACL-2007.
  • QUOTE: This paper examines whether a learning based coreference resolver can be improved using semantic class knowledge that is automatically acquired from a version of the Penn Treebank in which the noun phrases are labeled with their semantic classes. Experiments on the ACE test data show that a resolver that employs such induced semantic class knowledge yields a statistically significant improvement of 2% in F-measure over one that exploits heuristically computed semantic class knowledge. In addition, the induced knowledge improves the accuracy of common noun resolution by 2-6%.

• (Ng, 2007b) ⇒ Vincent Ng, (2007). “Shallow Semantics for Coreference Resolution.” In: Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007).

• (Culotta et al., 2007) ⇒ Aron Culotta, Michael Wick, Robert Hall, and Andrew McCallum. (2007). “First-order probabilistic models for coreference resolution.” In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT-NAACL 2007).
  • QUOTE: Noun phrase coreference resolution is the problem of clustering noun phrases into anaphoric sets. A standard machine learning approach is to perform a set of independent binary classifications of the form “Is mention a coreferent with mention b?” This approach of decomposing the problem into pairwise decisions presents at least two related difficulties. First, it is not clear how best to convert the set of pairwise classifications into a disjoint clustering of noun phrases. The problem stems from the transitivity constraints of coreference: If a and b are coreferent, and b and c are coreferent, then a and c must be coreferent.

2006

• Andrew McCallum. (2006). Information extraction, Data Mining and Joint Inference. KDD-2006. notes.
  • QUOTE: Traditionally in NLP co-reference has been performed by making independent coreference decisions on each pair of entity mentions. An Affinity Matrix CRF jointly makes all coreference decisions together, accounting for multiple constraints.”
• (McCallum, 2006) ⇒ Andrew McCallum. (2006). “Information Extraction: Coreference and Relation Extraction. Lecture #20, Computational Linguistics, CMPSCI 591N, Spring 2006 http://www.cs.umass.edu/~mccallum/courses/inlp2007/lect20-coref.ppt.pdf
  • QUOTE: Why is Coreference Resolution Hard

Many sources of information play a role
– head noun matches
* IBM executives = the executives
– syntactic constraints
* John helped himself to...
* John helped him to…
– number and gender agreement
– discourse focus, recency, syntactic parallelism, semantic class, world knowledge, …

** No single source is a completely reliable indicator
– number agreement
* the assassination = these murders
* Identifying each of these features automatically, accurately, and in context, is hard
* Coreference resolution subsumes the problem of pronoun resolution…

2005

• (Bekkerman and McCallum, 2005) ⇒ Ron Bekkerman and Andrew McCallum. (2005). “Disambiguating Web Appearance of People in a Social Network.” In: Proceedings of the 14th International World Wide Web Conference. (WWW 2005). doi:10.1145/1060745.1060813

2004

• Hema Raghavan, James Allan and Andrew McCallum. (2004). “An Exploration of Entity Models, Collective Classification and Relation Description.” In: KDD '04.
  • QUOTE: A simple language model with a fixed size window of n words.
• (Olsson, 2004) ⇒ Fredrik Olsson. (2004). “A Survey of Machine Learning for Reference Resolution in Textual Discourse." Technical Report, Swedish Institute of Computer Science.
• (Wellner et al., 2004) ⇒ Ben Wellner, Andrew McCallum, Fuchun Peng, and Michael Hay. (2004). “An Integrated, Conditional Model of Information Extraction and Coreference with Application to Citation Matching.” In: Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI 2004).

2003

• (Yang et al., 2003) ⇒ X. Yang, G. Zhou, J. Su, and C. L. Tan. (2003). Coreference resolution using competition learning approach. ACL. http://portal.acm.org/citation.cfm?id=1075096.1075119

2002

• Bansal, Blum, Chawla, 2002
• V. Ng and C. Cardie. (2002). Improving machine learning approaches to coreference resolution. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pages 104–111, Philadelphia.
  • Notes: Proposes a Pairwise Comparison Coreference Resolution Algorithm

2001

• (Soon et al., 2001) ⇒ Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. (2001). “A Machine Learning Approach to Coreference Resolution of Noun Phrases.” In: Computational Linguistics, Vol. 27, No. 4.
  • It proposes a Pairwise Classification Coreference Resolution Algorithm

1999

• (Wagstaff and Cardie, 1999) ⇒ Kiri Wagstaff, and Claire Cardie. (1999). “Noun Phrase Coreference as Clustering.” In: Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, 82-89, Association for Computational Linguistics, 1999.
  • It proposes an Unsupervised Learning Algorithm to the Entity Mention Coreference Resolution Task (Noun Phrase Coreference Resolution).
  • It requires Noun Phrase Detection (but no Full Syntactic Parse).
  • It focuses on Base Noun Phrases (not Complex Noun Phrases).
  • It handles several types of Noun Phrase Coreference Resolution, not just Pronoun Resolution.
  • It does not learn the weights associated with each term in the distance metric.

1995

• (McCarthy & Lehnert, 1995) ⇒ Joseph F. McCarthy, and Wendy G. Lehnert. (1995). “Using Decision Trees for Coreference Resolution.” In: Proceedings of the 14th International Joint Conference on Artificial Intelligence (IJCAI 1995)
  • Notes: It proposes a Pairwise Comparison Coreference Resolution Algorithm

TBd

• (Aone & Bennett, 1995) ⇒ C. Aone and S. W. Bennett. (1995). “Evaluating Automated and Manual Acquisition of Anaphora Resolution Strategies.” In: Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 122–129.
  • Notes: It proposes a Pairwise Comparison Coreference Resolution Algorithm

• Andrew McCallum. Conditional Models of Identity Uncertainty with Application to Noun Coreference

• Nanda Kambhatla, "Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Extracting Relations"
  • A maximum entropy approach to extract relations using lexical, syntactic and semantic features

---

@inproceedings{Luo:2005:crp,
 author = {Luo, Xiaoqiang},
 title = {On Coreference Resolution Performance Metrics},
 booktitle = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
 publisher = {Association for Computational Linguistics},
 address = {Vancouver, British Columbia, Canada},
 year = {2005},
 url = {http://www.aclweb.org/anthology/H/H05/H05-1004}
}

---