--- title: "Centering: A Framework for Modeling the Local — Grosz 1995" description: "The paper gives the definitive statement of centering, a model of the local attentional state inside one discourse segment. Each utterance has a ranked…" authors: ["Barbara J. Grosz", "Aravind K. Joshi", "Scott Weinstein"] year: 1995 venue: "Computational Linguistics" source: "https://aclanthology.org/J95-2003/" doi: "10.21236/ada324949" 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/cl-1995-grosz-centering-framework-modeling-local-coherence/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/cl-1995-grosz-centering-framework-modeling-local-coherence/) [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/) / Centering: A Framework for Modeling the Local Coherence of Discourse # Centering: A Framework for Modeling the Local Coherence of Discourse **Authors:** Barbara J. Grosz, Aravind K. Joshi, Scott Weinstein · **Year:** 1995 · **Venue:** Computational Linguistics 21(2) **Link:** [aclanthology.org/J95-2003](https://aclanthology.org/J95-2003/) · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only [**1773** citations](https://openalex.org/works?filter=cites:W2124741472) OpenAlex · 2026-10-14 · [**328** citations in our library](https://md.research.elamur.ai/free/en/papers/cl-1995-grosz-centering-framework-modeling-local-coherence/cited-by/) of the 140884 papers whose bibliographies we read · [Computational Linguistics](https://aclanthology.org/volumes/J95-2/) · [licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/J95-2003/) - [PDF](https://aclanthology.org/J95-2003.pdf) - [DOI 10.21236/ada324949](https://doi.org/10.21236/ada324949) - [OpenAlex](https://openalex.org/W2124741472) **Authors (3)** 1. [Barbara J. Grosz](https://openalex.org/A5015737731) [ORCID](https://orcid.org/0000-0003-3031-5591) · [Semantic Scholar](https://www.semanticscholar.org/author/2242855749) · h 43 · 13252 citations · 252 works 2. [Aravind K. Joshi](https://openalex.org/A5109994521) [Semantic Scholar](https://www.semanticscholar.org/author/2246491298) · h 58 · 15617 citations · 302 works 3. [Scott Weinstein](https://openalex.org/A5059611286) [ORCID](https://orcid.org/0000-0003-1002-2521) · [Semantic Scholar](https://www.semanticscholar.org/author/145092158) · h 25 · 4550 citations · 100 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about The paper gives the definitive statement of centering, a model of the local attentional state inside one discourse segment. Each utterance has a ranked set of forward-looking centers (Cf), mostly ordered by grammatical role, and exactly one backward-looking center (Cb), which is the highest-ranked center of the previous utterance that the current one realizes. Two rules follow: if any center is a pronoun, the Cb must be a pronoun too (Rule 1), and transitions are preferred in the order continue, retain, shift (Rule 2). The paper is a theory, not an evaluation. Its examples (John and Mike, Susan and Betsy, the Vice-President) show that breaking Rule 1 or running many shifts lowers coherence and raises the hearer's inference load, and the authors say the rules had no psycholinguistic test yet (section 6). ## Ideas - I1. Use the Cb as a tie-breaker in the coref sieve. Per sentence, rank the mentions by UD role (nsubj above obj above other) and prefer the previous sentence's Cb as the antecedent of a pronoun. Each link gets the reason "Cb continued", so `explain` shows it. Measure with the coref eval on GUM, two-fold `cv`, and two identical runs before any claim. - I2. Rule 1 as a warning, not a rule. When a pronoun points to a non-Cb entity while the Cb is a name, emit a flag in the explain output. Count how often the flag fires on correct links and on wrong ones. It is a precision check on the sieve, and it changes no link. - I3. Transition labels (continue, retain, shift) per paragraph as a coherence diagnostic in the world's tale readers. Negative control: the same paragraphs with shuffled sentence order must show more shifts. If they do not, the labels measure nothing. - I4. Value-free and value-loaded readings of role nouns ("the Vice-President") in `onto`: a role concept and its current holder are separate nodes, and a pronoun links to one of them with a reason that says which. Write our own test sentences; do not copy the paper's examples. ## For Mova The chapter is [languages/en/35-reference-and-coreference.md](https://mova.elamur.ai/free/en/docs/languages/en/35-reference-and-coreference/). The code is `coref/src/sieve.rs` and `coref/src/mention.rs`, the tale readers in `world`, and the role nouns in `onto`. The measure is the coref eval on GUM; check that corpus's licence in [licence/DATA.md](https://mova.elamur.ai/free/en/docs/licence/DATA/) before any release use. The paper is NC-SA: keep only these ideas in our words, and no text in the repo. Topics: [Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.21236/ada324949](https://doi.org/10.21236/ada324949) ```bibtex @article{grosz1995centering, title = {{Centering: A Framework for Modeling the Local Coherence of Discourse}}, author = {Grosz, Barbara J. and Joshi, Aravind K. and Weinstein, Scott}, journal = {Computational Linguistics}, year = {1995}, doi = {10.21236/ada324949}, url = {https://doi.org/10.21236/ada324949} } ``` - [← previous Anaphora Resolution in Machine Translation](https://md.research.elamur.ai/free/en/papers/mitkov-1995-anaphora-resolution-machine-translation/) - [next → CogNIAC: A Discourse Processing Engine](https://md.research.elamur.ai/free/en/papers/baldwin-1995-cogniac-discourse-processing-engine/) - [↑ back to papers of 1995](https://md.research.elamur.ai/free/en/papers/1995/) ## References 2 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Baldwin, Breck (1993). "Anaphora resolution with centering." In Workshop on Centering Theory in Naturally-Occurring Discourse. [find](https://scholar.google.com/scholar?q=Baldwin%2C+Breck+%281993%29%2E+%22Anaphora+resolution+with+centering%2E%22+In+Workshop+on+Centering+Theory+in+Naturally%2DOccurring+Discourse%2E) 2. Philadelphia, PA, May 1993. [find](https://scholar.google.com/scholar?q=Philadelphia%2C+PA%2C+May+1993%2E)