Anaphora Resolution System

An Anaphora Resolution System is a computing system that can solve an anaphora resolution task by implementing an anaphora resolution algorithm.

• AKA: Pronominal Anaphora Resolution System, Anaphora Coreference Resolution System, Anaphora Disambiguation System.
• Context:
  • It ranges from being a Pronominal Anaphora Resolution System, to being a Definite Noun Phrase Anaphora Resolution System, to being a One-Anaphora Resolution System.
  • …
• Example(s):
  • a Machine Learning Anaphora Resolution System such as:
    • Connolly-Burger-Day's Machine Learning Anaphora Resolution System (Connolly, Burger and Day 1994);
    • Aone-Bennett's Machine Learning Anaphora Resolution System (Aone & Bennet 1996);
  • a Statistical Anaphora Resolution System such as:
    • Mitkov's Linguistic-Statistical Anaphora Resolution System (Mitkov 1994; Mitkov 1996);
    • Statistical Corpus-based Anaphora Resolution System (Dagan & Itai);
  • a Syntax-based Anaphora Resolution System such as:
    • Hobbs Syntax-based Anaphora Resolution System (Hobbs 1976; Hobbs 1978);
    • Lappin-Leass Syntax-based Anaphora Resolution System (Lappin & Leass 1994);
    • Say-Vakman Punctuation-based Anaphora Resolution System (Say & Vakman 1996);
  • a Semantics-based Anaphora Resolution System such as:
    • Tin-Akman Situational Semantics Anaphora Resolution System (Tin & Akman 1994);
    • Wilks Preference Semantics Anaphora Resolution System (Wilks 1973),
  • a Knowledge-Poor Anaphora Resolution System such as:
    • Kennedy-Boguraev's Anaphora Resolution System;
    • Mikov's Robust Knowledge-Poor Anaphora Resolution System (Mitkov 1996, 1998);
    • Baldwin's COGNIAC Anaphora Resolution System,
  • a Machine Translation Anaphora Resolution System such as:
    • Wada's English-to-Japanese Machine Translation Anaphora Resolution System (Wada 1990);
    • Chen's English-to-Chinese Machine Translation Anaphora Resolution System (Chen 1992);
    • Saggion-Carvallho's Portuguese-to-English Machine Translation Anaphora Resolution System (Saggion & Carvalho 1994);
    • KIT-FAST English-to-German Machine Translation Anaphora Resolution System (Preub et al. 1994; Hauenschild et al. 1993);
    • Nakaiwa's Japanese Zero Pronouns Resolution System (Nakaiwa et al., 1991; Nakaiwa et al., 1994; Nakaiwa et al., 1995)
    • Mitkov's English-to-Korean Machine Translation Anaphora Resolution System (Mitkov et al. 1994);
    • CAT2 Anaphora Resolution System (Mitkov et al. 1995);
    • Voita-Serdyukov-Sennrich-Titov Context-Aware Neural Machine Translation Anaphora Resolution System (Voita et al., 2018),
  • an Information Extraction Anaphora Resolution System such as:
    • Kameyama's MUC-6 FASTUS Anaphora Resolution System (Kameyama 1997),
    • Azzam's M-LaSIE Pronoun Resolution System (Azzam et al. 1998),
  • STUDENT Anaphora Resolution System (Bobrow 1964),
  • SHRDLU Anaphora Resolution System (Winograd 1972),
  • Carter's Shallow Processing Anaphora Resolution System (Carter 1986),
  • Rich-LuperFoy's Distributed Pronominal Anaphora Resolution (Rich & LuperFoy 1988),
  • Carbonell-Brown's Multi-Strategy Anaphora Resolution System (Carbonell & Brown 1988),
  • Perez Scalar Product Coordinating Anaphora Resolution System (Rico Perez 1994),
  • Nasukawa's Knowledge-Independent Anaphora Resolution System,
  • Mitkov's Uncertainty-Reasoning Anaphora Resolution System (Mitkov 1995b),
  • Mitkov's Two-Engine Anaphora Resolution System (Mitkov 1997),
  • Athira's Salience-Score-based Malayalam Pronominal Anaphora Resolution System (Athira et al., 2014),
  • Liang-Wu Pronominal Anaphora Resolution System (Liang & Wu, 2004).
  • …
• Counter-Example(s):
  • a Noun-Phrase Coreference Resolution System
  • a Named Entity Disambiguation System,
  • a Synonym Extraction System.
• See: Natural Language Processing System, Natural Language Understanding System, Entity Mention Coreference Resolution System, Coreference Chain.

---

---

References

2018

• (Voita et al., 2018) ⇒ Elena Voita, Pavel Serdyukov, Rico Sennrich, and Ivan Titov. (2018). “Context-Aware Neural Machine Translation Learns Anaphora Resolution.” Proceedings of ACL 2018.

2009

• (Jurafsky & Martin, 2009) ⇒ Daniel Jurafsky, and James H. Martin. (2000). “Speech and Language Processing, 2nd edition.” Pearson Education.
  • We are now ready to two referent resolution tasks: coreference resolution and pronominal anaphora resolution. Coreference resolution is the task of finding referring expression in a text that refer to the same entity, that is, finding expression that corefer. We call the set of coreferring expressions a coreference chain.
  • Coreference resolution requires finding all referring expression in a discourse and group them into coreference chains. By contrast, pronomial anaphora resolution is the task of finding the antecedent for a single pronoun.

2006a

• (Bergsma and Lin, 2006)
  • found that ~97% of Anaphor Antecedents were Intrasentential Anaphora Mentions.

2006b

• (Haggerty, 2006) ⇒ James C. Haggerty. (2006). “Improving Pronoun Resolution.” Honours Thesis, School of Information Technologies, The University of Sydney, Australia.

2004

• (Liang & Wu, 2004) ⇒ Tyne Liang, and Dian-Song Wu. (2004). “Automatic Pronominal Anaphora Resolution in English Texts.” In: International Journal of Computational Linguistics & Chinese Language Processing. Special Issue on Selected Papers from ROCLING XV 9.1 (2004)., 9(1).

2002

• (Mitkov, 2002) ⇒ Ruslan Mitkov. (2002). “Anaphora Resolution.” In: Computational Linguistics.

2001

• (Garrod, 2001) ⇒ S. Garrod (2001). "Anaphora Resolution" In: International Encyclopedia of the Social & Behavioral Sciences Journal. DOI: 10.1016/B0-08-043076-7/01527-8
  • QUOTE: Anaphora occurs when there is repeated reference to the same entities in a discourse. Anaphora resolution is the process of interpreting the link between the anaphor (i.e., the repeated reference) and its antecedent (i.e., the previous mention of the entity). The process is of interest because it frequently involves interpretation across a sentence boundary. Thus, despite playing a crucial role in discourse comprehension, it falls outside the scope of traditional psycholinguistic accounts of sentence processing. There are two main issues that have driven the psychological research on anaphora resolution. First, there is the issue of how the resolution process relates to more basic sentence comprehension processes, such as syntactic parsing and semantic interpretation. This issue has been addressed principally by investigating the time course of anaphora resolution as compared with other sentence interpretation processes. The second issue concerns the nature of the mental representation of the discourse context that is required to support anaphora resolution. The research indicates that the process depends on access to mental models of discourse containing discourse entities that reflect the people and other things up to that point.

2000

• (Morton, 2000)
  • found that ~98.7% of Anaphor Antecedents were within two Sentences.

1999a

• (Mitkov, 1999) ⇒ Ruslan Mitkov. (1999). “Anaphora Resolution: The State of the Art.” In: Technical report. University of Wolverhampton.
  • QUOTE: Anaphora resolution is a complicated problem in Natural Language Processing and has attracted the attention of many researchers. The approaches developed - traditional (from purely syntactic ones to highly semantic and pragmatic ones), alternative (statistic, uncertainty-reasoning etc.) or knowledge-poor, offer only approximate solutions (...)

1999b

• (Strube and Hahn, 1999) ⇒ Michael Strube, and Udo Hahn. (1999). “Functional Centering Grounding Referential Coherence in Information Structure.” In: Computational Linguistics.
  • In establishing proper referential relations, we found the functional information structure of the utterances to be much more relevant. By this we mean indicators of whether or not a discourse entity in the current utterance refers to another discourse entity already introduced by previous utterances in the discourse. Borrowing terminology from Prince (1981, 1992), an entity that does refer to another discourse entity already introduced is called discourse-old or hearer-old, while an entity that does not refer to another discourse entity is called discourse-new or hearer-new.

1981

• (Hirst, 1981) ⇒ Graeme Hirst. (1981). “Anaphora in Natural Language Understanding: A Survey.” Springer-Verlag. ISBN:0387108580

1976

• (Halliday & Hasan, 1976) ⇒ Michael A. K. Halliday, and Ruqaiya Hasan. (1976). “Cohesion in English."Longman. ISBN:0582550416
  • QUOTE: "Anaphora is cohesion (presupposition) which points back to some previous item. The "pointing back" (reference) is called an anaphor and the entity to which it refers is its antecedent. The process of determining the antecedent of an anaphor is called anaphora resolution."

---