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 65 for “"response generation"”.
-
Response Generation in Longitudinal Dialogues
… the users' life-events and participants from the responses shared during each dialogue session, and create a personal user model. The acquired user model must consider individuals' states, profiles, and experiences that vary among users and dialogue sessions. The acquisition of a dialogue corpus …
-
Specific response generation and elaborative discourse structure
… better discourse structure in natural language generation by understanding how to control specificity in generation and what details to provide. The first part of the thesis explores techniques to control the specificity in dialogue response generation and tackles the plausibility issues that …
-
Dialog Response Generation Using Adversarially Learned Latent Bag-of-Words
Dialog response generation is the task of generating response utterance given a query utterance. Apart from generating relevant and coherent responses, one would like the dialog generation model to generate diverse and informative sentences. In this work, we propose and explore a novel multi-stage …
-
Using Response Generation Behaviors to Improve the Quality of Survey Data
… between respondent attributes and their responses. This research explores how a respondent’s response generation data manifests in their human computer interaction (HCI) device usage; and how these fine-grained HCI data may be used to identify poor-quality responses in online surveys. The …
-
Rethinking theory of mind measurement in neurotypical adults: response generation and selection
… interpretations, and the role of context in the generation and selection of mental state interpretations. The results challenged the notion of a single best mental state interpretation of ambiguous social stimuli, revealing multiple popular interpretations among participants that varied between …
-
The Effects of Differential Task Instructions and Motivational States on Individual Creative Response Generation
The extent to which creative response generation may be affected by motivation orientation and task instruction was investigated in the context of Amabile's (1983) model of creativity. A three-way mixed design with repeated measures across a time factor was employed using 104 undergraduate students …
-
THE ROLE OF HISTONE DEMETHYLASE JMJD3 IN THE INFLAMMATORY RESPONSE: GENERATION AND ANALYSIS OF IN VIVO MODELS
… induced by the transcription factor NF- kB in response to microbial stimuli. Jmjd3 erases trimethylated lysine 27 in histone H3 (H3K27me3), a histone mark associated with transcriptional repression and involved in lineage determination, differentiation and tissue homeostasis. However, the …
-
Personalization and Evaluation of Conversational Information Access
… personal context extraction, (2) personalized response generation, and (3) effective and interpretable system evaluation. First, we tackle personal context extraction by studying what Entity Linking (EL) in conversations entails, introducing a dataset for conversational entity linking (ConEL), …
-
Persona-based target-guided dialogue systems: A use case in dementia care
… and life stories. Then, we train a GPT-2 response generation model which leverages the extracted personas to generate personalised responses that preserve the identity of the individual, and train a keyword prediction kernel model to guide a conversation towards a given target topic. We …
-
Human-Centered Interactive Information Seeking
… in a conversation, the AI agent should compose a response grounded in relevant information from a knowledge source. In this thesis, we introduce our proposed solutions to three pivotal challenges in this interactive process. First, identifying relevant knowledge to be used in conversational …
-
Deep Latent Variable Models for Text Modelling
… tasks ranging from image synthesis to dialogue response generation. For instance, implicit linguistic cues such as topic information are helpful for various text modelling tasks, e.g., language modelling, dialogue response generation. Being able to accurately recognising dialogue acts plays a …
-
Dataset Augmentation for LLM Reasoning
… ways could lead the model to generate a better response. This thesis explores methods to augment the original dataset by systematically creating such variations of input-output pairs, with the goal of making reasoning more efficient. In the first part of this thesis, we explore how data …
-
An Intelligent Email Response System (IERS)
… In this work, we propose an intelligent email response system that performs three main steps: (i) automatically classify emails, (ii) detect questions or requests for information, and (iii) generate a response from a FAQ database or a knowledge base. In the first stage, we explore email …
-
Eye Movement Measures of Cognitive Control In Children With to urette Syndrome
… deficits in the cognitive control functions of response inhibition, response generation, and working memory have long been ascribed to Tourette Syndrome. Yet, without considering the effect of medication, age, and comorbidity, this is a premature attribution. This study used an infrared eye …
-
Trustworthy, Socially Responsible, and Knowledge-Grounded Conversational AI
… Furthermore, these systems often exhibit neural response generation artifacts, such as inconsistency, incoherence, inappropriateness, and repetition, which undermine their trustworthiness and impact. Additionally, mission-critical applications in domains like finance and healthcare cannot rely on …
-
Dialogue Act Tagging and Argument Extraction for Representing Debates in Conversational Agents
… neural models for dialogue analysis and response generation. The first contribution of the thesis is the design and development of DASHNet, a neural architecture for the classification of Dialogue Act Tags according to the ISO 24617-2 standard taxonomy. The architecture achieves …
-
ENHANCING CONVERSATIONAL AGENTS: SOURCE-AWARE GENERATION AND CONVERSATIONAL PARTNER UNDERSTANDING
… conversational agents by improving source-aware response generation and conversational partner understanding. For source-aware generation, it explores text documents and multimedia (images/videos). In text-based dialogues, it introduces knowledge sequence modeling for coherence and engagement and …
-
Retrieval Augmented Chatbots powered by Large Language Models for Semantically Structured Data
… structured data persist. Retrieval-Augmented Generation (RAG) systems address these issues by grounding LLMs in external knowledge. However, conventional RAG methods typically treat knowledge sources as unstructured text, overlooking the semantic relationships vital in domains like enterprise …
Page 1 of 4