• Login
    View Item 
    •   Home
    • UA Faculty Research
    • UA Faculty Publications
    • View Item
    •   Home
    • UA Faculty Research
    • UA Faculty Publications
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of UA Campus RepositoryCommunitiesTitleAuthorsIssue DateSubmit DateSubjectsPublisherJournalThis CollectionTitleAuthorsIssue DateSubmit DateSubjectsPublisherJournal

    My Account

    LoginRegister

    About

    AboutUA Faculty PublicationsUA DissertationsUA Master's ThesesUA Honors ThesesUA PressUA YearbooksUA CatalogsUA Libraries

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    A scaffolding approach to coreference resolution integrating statistical and rule-based models

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    nle17preprint.pdf
    Size:
    814.1Kb
    Format:
    PDF
    Description:
    Final Accepted Manuscript
    Download
    Author
    LEE, HEEYOUNG
    Surdeanu, Mihai
    JURAFSKY, DAN
    Affiliation
    Univ Arizona
    Issue Date
    2017-09
    
    Metadata
    Show full item record
    Publisher
    CAMBRIDGE UNIV PRESS
    Citation
    LEE, H., SURDEANU, M., & JURAFSKY, D. (2017). A scaffolding approach to coreference resolution integrating statistical and rule-based models. Natural Language Engineering, 23(5), 733-762. doi:10.1017/S1351324917000109
    Journal
    NATURAL LANGUAGE ENGINEERING
    Rights
    Copyright © Cambridge University Press 2017.
    Collection Information
    This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.
    Abstract
    We describe a scaffolding approach to the task of coreference resolution that incrementally combines statistical classifiers, each designed for a particular mention type, with rule-based models (for sub-tasks well-matched to determinism). We motivate our design by an oracle-based analysis of errors in a rule-based coreference resolution system, showing that rule-based approaches are poorly suited to tasks that require a large lexical feature space, such as resolving pronominal and common-noun mentions. Our approach combines many advantages: it incrementally builds clusters integrating joint information about entities, uses rules for deterministic phenomena, and integrates rich lexical, syntactic, and semantic features with random forest classifiers well-suited to modeling the complex feature interactions that are known to characterize the coreference task. We demonstrate that all these decisions are important. The resulting system achieves 63.2 F1 on the CoNLL-2012 shared task dataset, outperforming the rule-based starting point by over seven F1 points. Similarly, our system outperforms an equivalent sieve-based approach that relies on logistic regression classifiers instead of random forests by over four F1 points. Lastly, we show that by changing the coreference resolution system from relying on constituent-based syntax to using dependency syntax, which can be generated in linear time, we achieve a runtime speedup of 550 per cent without considerable loss of accuracy.+
    Note
    6 month embargo; published online: 21 March 2017
    ISSN
    1351-3249
    1469-8110
    DOI
    10.1017/S1351324917000109
    Version
    Final accepted manuscript
    Additional Links
    https://www.cambridge.org/core/product/identifier/S1351324917000109/type/journal_article
    ae974a485f413a2113503eed53cd6c53
    10.1017/S1351324917000109
    Scopus Count
    Collections
    UA Faculty Publications

    entitlement

     
    The University of Arizona Libraries | 1510 E. University Blvd. | Tucson, AZ 85721-0055
    Tel 520-621-6442 | repository@u.library.arizona.edu
    DSpace software copyright © 2002-2017  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service operated by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.