Georgetown University LogoGeorgetown University Library LogoDigitalGeorgetown Home
    • Login
    View Item 
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Computer Science
    • Graduate Theses and Dissertations - Computer Science
    • View Item
    •   DigitalGeorgetown Home
    • Georgetown University Institutional Repository
    • Georgetown College
    • Department of Computer Science
    • Graduate Theses and Dissertations - Computer Science
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Effective and Practical Neural Ranking

    Cover for Effective and Practical Neural Ranking
    View/Open
    View/Open: MacAvaney_georgetown_0076D_14817.pdf (2.5MB) Bookview

    Creator
    MacAvaney, Sean
    Advisor
    Goharian, Nazli
    Frieder, Ophir
    ORCID
    0000-0002-8914-2659
    Abstract
    Supervised machine learning methods that use neural networks (“deep learning”) have yielded substantial improvements to a multitude of Natural Language Processing (NLP) tasks in the past decade. Improvements to Information Retrieval (IR) tasks, such as ad-hoc search, lagged behind those in similar NLP tasks, despite considerable community efforts. Although there are several contributing factors, I argue in this dissertation that early attempts were not more successful because they did not properly consider the unique characteristics of IR tasks when designing and training ranking models. I first demonstrate this by showing how large-scale datasets containing weak relevance labels can successfully replace training on in-domain collections. This technique improves the variety of queries encountered when training and helps mitigate concerns of over-fitting particular test collections. I then show that dataset statistics available in specific IR tasks can be easily incorporated into neural ranking models alongside the textual features, resulting in more effective ranking models. I also demonstrate that contextualized representations, particularly those from transformer-based language models, considerably improve neural ad-hoc ranking performance. I find that this approach is neither limited to the task of ad-hoc ranking (as demonstrated by ranking clinical reports) nor English content (as shown by training effective cross-lingual neural rankers). These efforts demonstrate that neural approaches can be effective for ranking tasks. However, I observe that these techniques are impractical due to their high query-time computational costs. To overcome this, I study approaches for offloading computational cost to index-time, substantially reducing query-time latency. These techniques make neural methods practical for ranking tasks. Finally, I take a deep dive into better understanding the linguistic biases of the methods I propose compared to contemporary and traditional approaches. The findings from this analysis highlight potential pitfalls of recent methods and provide a way to measure progress in this area going forward.
    Description
    Ph.D.
    Permanent Link
    http://hdl.handle.net/10822/1062317
    Date Published
    2021
    Subject
    Computer science; Computer science;
    Type
    thesis
    Publisher
    Georgetown University
    Extent
    240 leaves
    Collections
    • Graduate Theses and Dissertations - Computer Science
    Metadata
    Show full item record

    Related items

    Showing items related by title, author, creator and subject.

    • Thumbnail

      Ethical Principles of the American Psychological Association: An Argument for Philosophical and Practical Ranking 

      Hadjistavropoulos, Thomas; Malloy, David Cruise (1999)
      Unlike the American Psychological Association (APA), the Canadian Psychological Association has adopted a code of ethics in which principles are organized in order of importance. The validity of this hierarchical organization ...
    Related Items in Google Scholar

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility
     

     

    Browse

    All of DigitalGeorgetownCommunities & CollectionsCreatorsTitlesBy Creation DateThis CollectionCreatorsTitlesBy Creation Date

    My Account

    Login

    Statistics

    View Usage Statistics

    Georgetown University Seal
    ©2009 - 2022 Georgetown University Library
    37th & O Streets NW
    Washington DC 20057-1174
    202.687.7385
    digitalscholarship@georgetown.edu
    Accessibility