Now showing items 1-20 of 26

    • AfriBERTa: Towards Viable Multilingual Language Models for Low-resource Languages 

      Ogueji, Kelechi (University of Waterloo, 2022-08-29)
      There are over 7000 languages spoken on earth, but many of these languages suffer from a dearth of natural language processing (NLP) tools. Multilingual pretrained language models have been introduced to help alleviate ...
    • Analytics for Everyone 

      El Gebaly, Kareem (University of Waterloo, 2018-05-23)
      Analyzing relational data typically involves tasks that facilitate gaining familiarity or insights and coming up with findings or conclusions based on the data. This process is usually practiced by data experts, such as ...
    • Cross-Domain Sentence Modeling for Relevance Transfer with BERT 

      Akkalyoncu Yilmaz, Zeynep (University of Waterloo, 2019-12-16)
      Standard bag-of-words term-matching techniques in document retrieval fail to exploit rich semantic information embedded in the document texts. One promising recent trend in facilitating context-aware semantic matching has ...
    • Cross-Lingual Entity Matching for Knowledge Graphs 

      Yang, Hsiu-Wei (University of Waterloo, 2020-12-14)
      Multilingual knowledge graphs (KGs), such as YAGO and DBpedia, represent entities in different languages. The task of cross-lingual entity matching is to align entities in a source language with their counterparts in target ...
    • dstlr: Scalable Knowledge Graph Construction from Text Collections 

      Clancy, Ryan (University of Waterloo, 2020-04-06)
      In recent years, the amount of data being generated for consumption by enterprises has increased exponentially. Enterprises typically work with structured data, but oftentimes the data being generated is semi-structured ...
    • Effective Math-Aware Ad-Hoc Retrieval based on Structure Search and Semantic Similarities 

      Zhong, Wei (University of Waterloo, 2023-09-15)
      Despite the prevalence of digital scientific and educational contents on the Internet, only a few search engines are capable to retrieve them efficiently and effectively. The main challenge in freely searching scientific ...
    • Efficient Inference of Transformers in Natural Language Processing: Early Exiting and Beyond 

      Xin, Ji (University of Waterloo, 2023-01-24)
      Large-scale pre-trained transformer models such as BERT have become ubiquitous in Natural Language Processing (NLP) research and applications. They bring significant improvements to both academia benchmarking tasks and ...
    • End-to-end Neural Information Retrieval 

      Yang, Wei (University of Waterloo, 2019-04-30)
      In recent years we have witnessed many successes of neural networks in the information retrieval community with lots of labeled data. Yet it remains unknown whether the same techniques can be easily adapted to search ...
    • An Experimental Analysis of Multi-Perspective Convolutional Neural Networks 

      Tu, Zhucheng (University of Waterloo, 2018-05-16)
      Modelling the similarity of sentence pairs is an important problem in natural language processing and information retrieval, with applications in tasks such as paraphrase identification and answer selection in question ...
    • Exploiting Token and Path-based Representations of Code for Identifying Security-Relevant Commits 

      Keshav Ram, Achyudh Ram (University of Waterloo, 2020-07-15)
      Public vulnerability databases such as CVE and NVD account for only 60% of security vulnerabilities present in open-source projects and are known to suffer from inconsistent quality. Over the last two years, there has been ...
    • Facilitating Information Access for Heterogeneous Data Across Many Languages 

      Shi, Peng (University of Waterloo, 2023-01-25)
      Information access, which enables people to identify, retrieve, and use information freely and effectively, has attracted interest from academia and industry. Systems for document retrieval and question answering have ...
    • Generalization on Text-based Games using Structured Belief Representations 

      Adhikari, Ashutosh Devendrakumar (University of Waterloo, 2020-12-23)
      Text-based games are complex, interactive simulations where a player is asked to process the text describing the underlying state of the world to issue textual commands for advancing in a game. Playing these games can be ...
    • Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting 

      Lee, Jaejun (University of Waterloo, 2019-12-19)
      Used for simple voice commands and wake-word detection, keyword spotting (KWS) is the task of detecting pre-determined keywords in a stream of utterances. A common implementation of KWS involves transmitting audio samples ...
    • An In-Depth Exploration of the High-Quality Entity Linking for Information Retrieval: MMEAD 

      Lin, Luyun (University of Waterloo, 2023-12-19)
      Entity linking has emerged significantly during the digital information explosion, aiming to provide context and meaning to huge amounts of unstructured data. While traditional information retrieval primarily relied on ...
    • Information Access Using Neural Networks For Diverse Domains And Sources 

      Xie, Yuqing (University of Waterloo, 2023-09-05)
      The ever-increasing volume of web-based documents poses a challenge in efficiently accessing specialized knowledge from domain-specific sources, requiring a profound understanding of the domain and substantial comprehension ...
    • Learning to Rank in the Age of Muppets 

      Hu, Chengcheng (University of Waterloo, 2022-04-26)
      The emergence of BERT in 2018 has brought a huge boon to retrieval effectiveness in many tasks across various domains and led the recent research landscape of IR to transformer-related technologies. While researchers ...
    • Less is More: Restricted Representations for Better Interpretability and Generalizability 

      Jiang, Zhiying (University of Waterloo, 2023-08-22)
      Deep neural networks are prevalent in supervised learning for large amounts of tasks such as image classification, machine translation and even scientific discovery. Their success is often at the sacrifice of interpretability ...
    • The Limited Effectiveness of Neural Networks for Simple Question Answering on Knowledge Graphs 

      Mohammed, Salman (University of Waterloo, 2017-12-08)
      Simple factoid question answering (QA) is a task, where the questions can be answered by looking up a single fact in the knowledge base (KB). However, this QA task is difficult, since retrieving a single supporting fact ...
    • Machine Learning for Streamflow Prediction 

      Gauch, Martin (University of Waterloo, 2020-04-16)
      Accurate prediction of streamflow—the amount of water flowing past a stream section at a given time—is a long-standing challenge in hydrology. Not only do researchers strive to understand the natural processes at play, the ...
    • Neural Text Generation from Structured and Unstructured Data 

      Shahidi, Hamidreza (University of Waterloo, 2019-08-28)
      A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least ...

      UWSpace

      University of Waterloo Library
      200 University Avenue West
      Waterloo, Ontario, Canada N2L 3G1
      519 888 4883

      All items in UWSpace are protected by copyright, with all rights reserved.

      DSpace software

      Service outages