UMD Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/3

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Filters

2013 - 201912020 - 20221

Settings

Author: search.filters.author.Zhao, Chen

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    TOWARDS PRACTICAL COMPLEX QUESTION ANSWERING
    (2022) Zhao, Chen; Boyd-Graber, Jordan; Daume III, Hal; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Question answering (QA) is one of the most important and challenging tasks for understanding human language. With the help of large-scale benchmarks, there is tremendous success on building neural QA systems, and such progress has been deployed into commercial systems like search engines. However, most QA systems target rather simple questions that can be answered within a single evidence piece (e.g., a sentence). In many real scenarios, users also ask complex questions that require multiple evidence pieces, and search engines fail to answer them. The goal of this dissertation work is to tackle complex QA problem from different angles.We first study complex QA using text collections as a knowledge source. We build two QA systems that rely on a free-text knowledge graph from Wikipedia. Through extracting a question grounded sub-graph and using graph neural network to reason over this graph, the proposed QA systems are state-of-the-art on multiple complex QA benchmarks. Then we present two solutions to address some key assumptions that make state-of-the-art QA systems difficult to generalize beyond specific benchmarks. We first address the assumption that the given text collections is semi-structured by hyperlinks. We propose a multi-step dense retrieval method to model the implicit relationships between evidence pieces. The retriever is competitive to state-of-the-arts on complex QA benchmarks, without using any semi-structured information. To further address the assumption that annotated evidence labels are given during training, we focus on the weakly-supervised setting, with only question-answer pairs available. We propose an iterative approach that improves over a weak retriever by alternately finding evidence from the up-to-date model, and encouraging the model to learn the most likely evidence. Without using any evidence labels, our approach is on par with fully-supervised counterparts. We also study complex QA using tables as a knowledge source. We focus on a practical problem that is dismissed by benchmarks: domain generalization on mathematical operation over columns. We first construct benchmarks to quantify this problem, then we address this problem by incorporating the necessary domain knowledge through table schema preprocessing. Our approach significantly outperforms baselines on this problem, and as a result, boosts the overall performance.
  • Thumbnail Image
    Item
    Information Harbor: The Transformation of a Historic Chinese Village
    (2013) Zhao, Chen; Noonan, Peter Noonan; Architecture; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    In modern-day China, policies have been enacted to foster stronger bonds between urban and rural areas in an attempt to bridge the gap in economic and informational inequality. Until now Chinese officials have made very little attempt to salvage decaying rural villages that still have value to society. As a response, how might one apply Critical Regionalist theory to an historic Chinese village and transform it from a bleak village into an energetic and educational tourist destination? Based on the research of traditional Chinese building culture and modern technology integration, a series of interventions are designed to address local dwellers' needs for contemporary information amenities in rural areas while also providing educational and recreational resources for city visitors and maximizing sustainability of the site. Baoshi Village has been chosen as a case study whose principles and strategies could also apply to the villages of similar size and situation throughout China.