--- title: "CogNIAC: A Discourse Processing Engine — Baldwin 1995" description: "This doctoral thesis describes CogNIAC, a pronoun and coreference resolution engine built around a small set of high-confidence rules applied in order.…" authors: ["Breck Baldwin"] year: 1995 venue: "Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts" source: "https://aclanthology.org/W97-1306/" licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/baldwin-1995-cogniac-discourse-processing-engine/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/baldwin-1995-cogniac-discourse-processing-engine/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1995](https://md.research.elamur.ai/free/en/papers/1995/) / CogNIAC: A Discourse Processing Engine # CogNIAC: A Discourse Processing Engine **Authors:** [Breck Baldwin](https://md.research.elamur.ai/free/en/authors/breck-baldwin/) · **Year:** 1995 · **Venue:** PhD thesis, University of Pennsylvania **Link:** unknown **License of the paper:** unknown **31** citations in our library of the 140673 papers whose bibliographies we read · [Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts](https://aclanthology.org/volumes/W97-13/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/W97-1306/) - [PDF](https://aclanthology.org/W97-1306.pdf) **Authors (1)** 1. Baldwin, Breck [Semantic Scholar](https://www.semanticscholar.org/author/144077739) Citations and author metrics: OpenAlex, ; authors with the same name are not always told apart. ## Summary This doctoral thesis describes CogNIAC, a pronoun and coreference resolution engine built around a small set of high-confidence rules applied in order. The philosophy is precision first: a pronoun is resolved only when a rule fires unambiguously, otherwise it is left unresolved, so that downstream applications get few but reliable links. The rules rely on limited knowledge and shallow linguistic resources, such as unique antecedents in the current and previous sentence, reflexives, and patterns in quoted speech. The work was later summarised in a shorter 1997 workshop paper ("CogNIAC: high precision coreference with limited knowledge and linguistic resources"). Further details of the thesis contents are not confirmed here. ## How Mova uses it - `coref/src/sieve.rs` (`find_quote_authors`) — determining who speaks in a quotation: in a sentence containing a quote, the author is the subject of a speech verb outside the quotation marks; speech verbs come from a closed hand-written list. A quote continuing into the next sentence without a new author keeps the same author. - The rule is cited together with Lee et al. 2013 (§3.3.1) and feeds the `speaker` sieve: first-person pronouns of one voice are one person, "you" addressed to someone links to that person's earlier "I". ## Effectiveness in Mova The quote-author rule is part of the `speaker` sieve, which in the development notes of `coref` (GUM test, gold trees, cumulative contribution) makes 771 links at 90.7% precision and adds +21.88 CoNLL F1 without singletons (+21.99 with Mova's own trees). That figure covers the whole sieve (also built on Lee et al. 2013); the contribution of the quote-author rule alone is not measured separately. --- 👨‍🔬💥 Topics: [Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) ## Cite The paper itself, not this card. BibTeX from the library's record of the work. ```bibtex @inproceedings{baldwin1997cogniac, title = {{CogNIAC: A Discourse Processing Engine}}, author = {Baldwin, Breck}, booktitle = {Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts}, year = {1997}, url = {https://aclanthology.org/W97-1306/} } ``` - [← previous Centering: A Framework for Modeling the Local Coherence of Discourse](https://md.research.elamur.ai/free/en/papers/cl-1995-grosz-centering-framework-modeling-local-coherence/) - [next → Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions](https://md.research.elamur.ai/free/en/papers/dale-1995-computational-interpretations-gricean-maxims-generation/) - [↑ back to papers of 1995](https://md.research.elamur.ai/free/en/papers/1995/) ## References 14 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Baldwin, B., "CogNIAC: A discourse processing engine", University of Pennsylvania, Department of Computer and Information Science, Ph.D. dissertation. [find](https://scholar.google.com/scholar?q=Baldwin%2C+B%2E%2C+%22CogNIAC%3A+A+discourse+processing+engine%22%2C+University+of+Pennsylvania%2C+Department+of+Computer+and+Information+Science%2C+Ph%2ED%2E+dissertation%2E) 2. Baldwin, B., Reynar, J., Collins, M., Eisner, J., Ratnaparkhi, A., Rosenzweig, J., Sarkar, A., Srinivas (1995), "University of Pennsylvania: Description of the University of Pennsylvania system used for MUC-6", Proceedings of Sixth Message Understanding Conference, November 1995. [find](https://scholar.google.com/scholar?q=Baldwin%2C+B%2E%2C+Reynar%2C+J%2E%2C+Collins%2C+M%2E%2C+Eisner%2C+J%2E%2C+Ratnaparkhi%2C+A%2E%2C+Rosenzweig%2C+J%2E%2C+Sarkar%2C+A%2E%2C+Srinivas+%281995%29%2C+%22University+of+Pennsylvania%3A+Description+of+the+University+of+Pennsylvania+system+used+f) 3. Collins, M., "A New Statistical Parser based on Bigram Lexical Dependencies", Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics, June, 1996. [find](https://scholar.google.com/scholar?q=Collins%2C+M%2E%2C+%22A+New+Statistical+Parser+based+on+Bigram+Lexical+Dependencies%22%2C+Proceedings+of+the+34th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+June%2C+1996%2E) 4. Carter, D. (1986), "Common Sense Inference in a Focus-Guided Anaphor Resolver", Journal of Semantics, 4. [find](https://scholar.google.com/scholar?q=Carter%2C+D%2E+%281986%29%2C+%22Common+Sense+Inference+in+a+Focus%2DGuided+Anaphor+Resolver%22%2C+Journal+of+Semantics%2C+4%2E) 5. Chinchor, N., Sundheim, B. (1994) "Coreference Task Definition vl.l", supporting documentation for MUC-6 coreference task. [find](https://scholar.google.com/scholar?q=Chinchor%2C+N%2E%2C+Sundheim%2C+B%2E+%281994%29+%22Coreference+Task+Definition+vl%2El%22%2C+supporting+documentation+for+MUC%2D6+coreference+task%2E) 6. Dagan, I., Itai, A., (1990) A Statistical Filter for Resolving Pronoun References, Proceedings of 7th Israeli Symposium on Artificial Intelligence and Computer Vision. [find](https://scholar.google.com/scholar?q=Dagan%2C+I%2E%2C+Itai%2C+A%2E%2C+%281990%29+A+Statistical+Filter+for+Resolving+Pronoun+References%2C+Proceedings+of+7th+Israeli+Symposium+on+Artificial+Intelligence+and+Computer+Vision%2E) 7. Grosz, B. J, Joshi, A. K., and Weinstein, S. (1986) "Towards a Computational Theory of Discourse Interpretation" Ms. [find](https://scholar.google.com/scholar?q=Grosz%2C+B%2E+J%2C+Joshi%2C+A%2E+K%2E%2C+and+Weinstein%2C+S%2E+%281986%29+%22Towards+a+Computational+Theory+of+Discourse+Interpretation%22+Ms%2E) 8. Hobbs, J. (1976) "Pronoun Resolution", Research Report \#76-1, City College, City University of New York. [find](https://scholar.google.com/scholar?q=Hobbs%2C+J%2E+%281976%29+%22Pronoun+Resolution%22%2C+Research+Report+%5C%2376%2D1%2C+City+College%2C+City+University+of+New+York%2E) 9. Hobbs, J. (1977) "38 Examples of Elusive Antecedents from Published Texts", Research Report \#77-2, City College, City University of New York. [find](https://scholar.google.com/scholar?q=Hobbs%2C+J%2E+%281977%29+%2238+Examples+of+Elusive+Antecedents+from+Published+Texts%22%2C+Research+Report+%5C%2377%2D2%2C+City+College%2C+City+University+of+New+York%2E) 10. C. Kennedy, B. Boguraev, "Anaphora for everyone: pronominal anaphora resolution without a parser." Proceedings of the 16th International Conference on Computational Linguistics COLING'96, Copenhagen, Denmark, 5-9 August 1996 [find](https://scholar.google.com/scholar?q=C%2E+Kennedy%2C+B%2E+Boguraev%2C+%22Anaphora+for+everyone%3A+pronominal+anaphora+resolution+without+a+parser%2E%22+Proceedings+of+the+16th+International+Conference+on+Computational+Linguistics+COLING%2796%2C+Copenhagen%2C+) [our card](https://md.research.elamur.ai/free/en/papers/kennedy-1996-anaphora-everyone-pronominal-anaphora-resolution/) 11. Lappin, S., Leass, H. (1994) "An Algorithm for Pronominal Anaphora Resolution", Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lappin%2C+S%2E%2C+Leass%2C+H%2E+%281994%29+%22An+Algorithm+for+Pronominal+Anaphora+Resolution%22%2C+Computational+Linguistics%2E) [our card](https://md.research.elamur.ai/free/en/papers/lappin-1994-algorithm-pronominal-anaphora-resolution/) 12. Mitkov R., "Pronoun resolution: the practical alternative", In S. Botley, T. McEnery (Eds) "Discourse Anaphora and Anaphor Resolution". University College London Press, 1997 [find](https://scholar.google.com/scholar?q=Mitkov+R%2E%2C+%22Pronoun+resolution%3A+the+practical+alternative%22%2C+In+S%2E+Botley%2C+T%2E+McEnery+%28Eds%29+%22Discourse+Anaphora+and+Anaphor+Resolution%22%2E+University+College+London+Press%2C+1997) 13. Sidner, C. L. (1986) "Focusing in the Comprehension of Definite Anaphora", Readings in Natural Language Processing, eds Grosz, Jones, Webber. Morgan Kaufman, Los Altos CA. [find](https://scholar.google.com/scholar?q=Sidner%2C+C%2E+L%2E+%281986%29+%22Focusing+in+the+Comprehension+of+Definite+Anaphora%22%2C+Readings+in+Natural+Language+Processing%2C+eds+Grosz%2C+Jones%2C+Webber%2E+Morgan+Kaufman%2C+Los+Altos+CA%2E) 14. Winograd, T. 1972, "Understanding Natural Language", New York: Academic Press. [find](https://scholar.google.com/scholar?q=Winograd%2C+T%2E+1972%2C+%22Understanding+Natural+Language%22%2C+New+York%3A+Academic+Press%2E)