Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"Auto-completion"”.
-
Data driven auto-completion for keyframe animation
… In this thesis, we present a data-driven autocompletion method for synthesizing animated motions from input keyframes. Our model uses an autoregressive two-layer recurrent neural network that is conditioned on target keyframes. Given a set of desired keys, the trained model is capable of …
-
Analyzing intentions from big data traces of human activities
… models. Specifically, we take query auto-completion as a case study. We identify two hitherto-undiscovered problems: adaptive query auto-completion and mobile query auto-completion. We develop two computational models by analyzing intentions from big data traces of human activities on …
-
Methods for design of efficient on-device natural language processing architectures
… for the manual design of architecture for the auto-completion task (generate continuations for user-written prompts) that enjoy a better memory-accuracy tradeoff than existing auto-completion models (Chapter 2). Additionally, we introduce methods that can directly take efficiency constraints to …
-
PaperKeys: On-screen Keyboard
… keyboards have. PaperKeys has a built-in auto-completion engine. Currently, it supports both English and Icelandic. The keyboard predicts a word based on what you are typing at any given moment and offers corrections for misspelled words.
-
Using interaction data for improving the offline and online evaluation of search engines
… accurate offline evaluation methods for query auto-completion mechanisms. We propose a family of offline evaluation metrics for query auto-completion that represents the effort the user has to spend in order to submit their query. The parameters of our proposed metrics are trained against a set …
-
Influence modeling in behavioral data
… interaction of search engine users with query auto-completion (QAC) engine within each query session. The fourth part of this work studies how a user's present interaction with a QAC engine influences his/her interaction in the next step. We propose a novel probabilistic model based on Markov …
-
LEVER: A Framework for DSL Editor Support
… to features such as syntax-highlighting, auto-completion, and context-aware renaming. Developing such tooling for DSLs is challenging due to the significant effort required to implement features from scratch. To address this problem, this thesis proposes Lever , a framework for building …
-
A systematic study of multi-level query understanding
… skipping bias which is unique to the query auto- completion process (QAC). I then proposed a novel two-dimensional click model for modeling the QAC process with emphasis on such behavior.
-
The Effects of AI Assisted Programming in Software Engineering
… Copilot can increase efficiency through auto-completion specifically. A lack of conversational capabilities and disruptive elements of Copilot lead to hindrances in development and code analysis. Furthermore, GAI tools allow engineers to focus on higher-level problems and offer …
-
Temporal dynamics in information retrieval
… users formulate queries through time-aware query auto-completion, which can suggest both recent and always popular queries. I propose and evaluate novel approaches for time-sensitive query auto-completion, and demonstrate state-of-the-art performance of up to 9.2% improvement above the hard …
-
Transformer-based Semantic Parsing of Building Regulations: Supporting Regulators in Drafting Machine-Interpretable Rules
… to ensure the safety of building occupants. Automated Compliance Checking (ACC) can guarantee the consistent application of all relevant building regulations to a building model. Since most countries’ building regulations are only available in natural language, much time, cost, and effort …
-
Efficient Methods for Knowledge Base Construction and Query
… learn more about the user queries. However, in automated knowledge base construction, ambiguity in data sources is one of the main challenges. Given a constructed knowledge base, it is hard to efficiently find entities of interest and extract their relatedness information from the knowledge base …
-
Optimal Path-Decomposition of Tries
In this thesis, we consider the path-decomposition representation of prefix trees. We show that given query probabilities for every word in the prefix tree, the heavy-path strategy produces the optimal trie with respect to the number of node accesses. We show how to implement the heavy-path …