Related papers: A Student-Teacher Architecture for Dialog Domain A…
Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…
Large Language Models have demonstrated remarkable capabilities in open-domain dialogues. However, current methods exhibit suboptimal performance in service dialogues, as they rely on noisy, low-quality human conversation data. This…
In this paper, we present an approach to incorporate retrieved datapoints as supporting evidence for context-dependent semantic parsing, such as generating source code conditioned on the class environment. Our approach naturally combines a…
Adaptive learning aims to stimulate and meet the needs of individual learners, which requires sophisticated system-level coordination of diverse tasks, including modeling learning resources, estimating student states, and making…
In many automatic speech recognition (ASR) tasks, an ideal model has to be applicable over multiple domains. In this paper, we propose to teach an all-rounder with experts in different domains. Concretely, we build a multi-domain acoustic…
In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…
Classroom dialogue plays a crucial role in fostering student engagement and deeper learning. However, analysing dialogue sequences has traditionally relied on either theoretical frameworks or empirical descriptions of practice, with limited…
Spoken dialogue systems (SDSs) have been separately developed under two different categories, task-oriented and chit-chat. The former focuses on achieving functional goals and the latter aims at creating engaging social conversations…
The cooperation among AI systems, and between AI systems and humans is becoming increasingly important. In various real-world tasks, an agent needs to cooperate with unknown partner agent types. This requires the agent to assess the…
Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system,…
Task-oriented dialog systems empower users to accomplish their goals by facilitating intuitive and expressive natural language interactions. State-of-the-art approaches in task-oriented dialog systems formulate the problem as a conditional…
A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whether the target…
Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applications. This paper systematically investigates domain…
Educational chatbots are a promising tool for assisting student learning. However, the development of effective chatbots in education has been challenging, as high-quality data is seldom available in this domain. In this paper, we propose a…
Machine Translation (MT) and Quality Estimation (QE) perform well in general domains but degrade under domain mismatch. This dissertation studies how to adapt MT and QE systems to specialized domains through a set of data-focused…
Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…
Mathematical learning environments help students in mastering mathematical knowledge. Mature environments typically offer thousands of interactive exercises. Providing feedback to students solving interactive exercises requires domain…
Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that…
Identifying the topic (domain) of each user's utterance in open-domain conversational systems is a crucial step for all subsequent language understanding and response tasks. In particular, for complex domains, an utterance is often routed…
Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of…