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 20 of 20 for “"Open Domain"”.
-
Towards open-domain event understanding
… original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-03-28 without embargo terms
-
Towards automated generation of open domain Wikipedia articles
The student, Yunqian Bao, accepted the attached license on 2023-07-20 at 11:40.
-
Augmenting Transformers for Open Domain Procedural Text Comprehesion
Recent advances in deep learning model architectures have permitted state-of-the-art results in various fields such as NLP and CV. Although these systems have matched and, in some cases, surpassed human performance, many of them are still treated as black boxes, with sometimes unpredictable …
-
Domain Playground: Extending Deep Learning Models to Open Domain Boundaries
… performance is only guaranteed when there is no domain gap (e.g., the distribution of the source and target data are similar). Domain adaptation is a specialized classification task that aims to mitigate the domain gap by transferring knowledge between domains, allowing flexible deep learning …
-
Towards Effective Long Conversation Generation: Dynamic Topic Tracking and Recommendation for Open-Domain Dialogue Systems
… effective topic management and evo- lution in open-domain dialogue systems. This thesis presents EvolvConv, a novel approach for real-time conversation topic tracking and evolution in AI dialogue systems. EvolvConv addresses critical limitations in existing open-domain dialogue systems, which …
-
Information Retrieval with Dense and Sparse Representations
… numerous applications such as search engines and open-domain question-answering systems, relies on effective textual representation and semantic matching. However, current approaches can lose nuanced lexical detail information due to an information bottleneck in dense retrieval, or rely on exact …
-
Encyclopaedic Question Answering
Open-domain question answering (QA) is an established NLP task which enables users to search for speciVc pieces of information in large collections of texts. Instead of using keyword-based queries and a standard information retrieval engine, QA systems allow the use of natural language questions …
-
Enhancing Retrieval Augmented Generation Through Robust Information Retrieval
… limitations of semantic similarity retrieval in open domain environments, indicating that lexical based algorithms are still relevant and the NFL (No Free Lunch) Theorem still applies in IR, as we notice that semantic similarity and lexical based approaches, excel in closed and open domain …
-
Integrating human-provided information into belief state representation using dynamic factorization
… them when they are not. This strategy works in open domains, in which the set of possible objects is not known in advance, and provides significant improvements in inference time, leading to more efficient planning for complex partially observable tasks. We validate our approach experimentally …
-
Optimizing Large Language Models from a Data SystemsPerspective
… a broad spectrum of downstream tasks, such as open-domain question answering and solving math or science problems. While current LLM-based frameworks achieve strong performance on complex retrieval and reasoning tasks, they do so at a high computational cost. Additionally, they often lack …
-
Learning meaning representations for text generation with deep generative models
… We investigate three language generation tasks: open domain conversational response generation, sentence generation from a semantic topic, and generating surface form realisations of meaning representations. We use a different type of auxiliary variable for each task, describe the reasons for …
-
Applying Wikipedia to Interactive Information Retrieval
… Wikipedia can be applied effectively to open-domain information retrieval with minimal natural language processing or information extraction. The key is to focus on gathering and applying human-readable rather than machine-readable knowledge. To demonstrate this claim, the thesis tackles …
-
Towards Human-Centered Optimality Criteria
… to approximate interactive human evaluation in open-domain dialog through self-play that is more strongly correlated with human evaluations than other automated metrics commonly used today. While dialog quality evaluation metrics predominantly use word-level overlap or distance metrics based on …
-
Augmenting Multi-modal Question Answering Systems with Retrieval Methods
… these models have revolutionised various domains. However, challenges persist, especially in incorporating extensive domain-specific knowledge and mitigating the generation illusion inherent in large language models. This thesis explores the integration of retrieval-augmented generation …
-
Response Generation in Longitudinal Dialogues
… acquisitions have been designed either for open-domain information retrieval or slot-filling tasks with stereotypical user models "\textit{averaged}" among users. In contrast, the level of personalization in LDs is beyond a set of personal preferences and can not be learned from a limited …
-
Investigation of water-in-oil emulsion on CSI solvent dissolution and ex-solution performance for heavy oil
… examined and has never been published in the open domain based on our best knowledge. More specifically, the water content of the emulsion oil influences the density, viscosity, IFT and phase behaviour of the heavy oil systems to different extents. After analyzing the experimental data, it was …
-
Interpretable Multi-hop Question Answering
… these proposed QA systems over multiple open-domain multi-hop QA datasets collected from Wikipedia, with the aim of helping computers to think and reason about natural language text.
-
Sample-Efficient Reinforcement Learning for Spoken Dialogue Systems
… adoption, the development of a general open-domain dialogue system capable of engaging in natural conversations with humans remains a challenging task. Developing effective dialogue systems poses a challenge in the face of non-deterministic environments. Users exhibit diverse behaviors, …
-
Mining entity and relation structures from text: An effort-light approach
… social media posts), covering topics in various domains (e.g., medical records, corporate reports, and legal acts). Can computational systems automatically identify various real-world entities mentioned in a new corpus and use them to summarize recent news events reliably? Can computational …
-
Building a question answering system for the introduction to statistics course using supervised learning techniques
… a question asked by a human in natural language. Open-domain QA is still a difficult problem to solve even after 60 years of research in this field, as trying to answer questions which cover a wide range of subjects is a complex matter. Closed-domain QA is, on the other hand, more achievable as …