Skip to main content
UMass Collegiate M The University of Massachusetts Amherst
  • Visit
  • Apply
  • Give
  • Search UMass.edu
Manning College of Information & Computer Sciences

Main navigation

  • Academics

    Programs

    Undergraduate Programs Master's Programs Doctoral Program Graduate Certificate Programs

    Academic Support

    Advising Career Development Academic Policies Courses Scholarships and Fellowships
  • Research

    Research

    Research Areas Research Centers & Labs Undergraduate Research Opportunities

    Faculty & Researchers

    Faculty Directory Faculty Achievements

    Engage

    Research News Distinguished Lecturer Series Rising Stars in Computer Science Lecture Series
  • Community

    On-Campus

    Diversity and Inclusion Student Organizations Massenberg Summer STEM Program Awards Programs Senior Celebration

    External

    Alumni Support CICS
  • People
    Full A-Z Directory Faculty Staff
  • About

    Overview

    College Overview Leadership Our New Building

    News & Events

    News & Stories Events Calendar

    Connect

    Visiting CICS Contact Us Employment Offices & Services
  • Info For
    Current Undergraduate Students Current Graduate Students Faculty and Staff Newly Accepted Undergraduate Students

PhD Seminar: Yen-Chieh Lien, Data Generation for Weakly Supervised Neural Retrieval

Content

Wednesday, January 29, 2025, 12:00 PM - Wednesday, January 29, 2025, 2:00 PM

Online
Theory Seminar
Seminar

Speaker

Yen-Chieh Lien

Abstract

To address the data limitation in neural retrieval, weak supervision  leverages existing ranking methods to automatically generate pseudo relevance judgments. However, there are still several limitations to consider. Firstly, the size and accessibility of the query collection pose challenges for existing methods in generating a sufficiently large and diverse set of weak signals. Secondly, while empirical and theoretical evidence demonstrates that a weakly supervised neural ranking model can outperform the original ranker, the quality of the information provided by the original ranking models highly correlates with and constrains the overall performance of weakly supervised models.

To overcome these limitations, the dissertation focuses on employing a neural generative approach for data generation in weak supervision settings, incorporating effective techniques. To address the issue of query scarcity, a query augmentation framework is designed, which utilizes GAN-based methods to expand an insufficient query set. Evaluation results indicate that augmentation enhances ranking performance, particularly when the original query set is inadequate for supporting weakly supervised training. In the context of E-commerce applications, an ensemble approach is devised to generate pseudo queries from customer reviews. These generated queries exhibit similarity to real customer queries and effectively enhance ranking performance within the weak supervision framework. To tackle the challenge of  
weak labeler quality, we propose a framework called generalized weak supervision (GWS). This framework extends the definition of weak labeler to include the weakly supervised model itself. Through iterative re-labeling, the quality of pseudo relevance judgments is improved without the need for additional data. We present four implementations of the GWS framework, demonstrating significant enhancements in ranking tasks compared to weak supervision methods. Finally, we extend weak signals generated from large language models (LLMs) to explanations in natural language. Through the extended form, the ranking ability of LLMs is transferred into smaller models more effectively.

Advisors

W. Bruce Croft and Hamed Zamani

Online event posted in Theory Seminar

More link

Join via Zoom

Site footer

Manning College of Information & Computer Sciences
  • Find us on Facebook
  • Find us on YouTube
  • Find us on LinkedIn
  • Find us on Instagram
  • Find us on Flickr
  • Find us on Bluesky Social
Address

140 Governors Dr
Amherst, MA 01003
United States

  • Visit CICS
  • Give
  • Contact Us
  • Employment
  • Events Calendar
  • Offices & Services

Info For

  • Current Undergraduate Students
  • Current Graduate Students
  • Faculty & Staff
  • Newly Accepted Undergraduate Students

Global footer

  • ©2025 University of Massachusetts Amherst
  • Site policies
  • Privacy
  • Non-discrimination notice
  • Accessibility
  • Terms of use