Related papers: Preview, Attend and Review: Schema-Aware Curriculu…
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then…
Multi-task Vehicle Routing Problems (VRPs) aim to minimize routing costs while satisfying diverse constraints. Existing solvers typically adopt a unified reinforcement learning (RL) framework to learn generalizable patterns across tasks.…
We investigate the task of learning to follow natural language instructions by jointly reasoning with visual observations and language inputs. In contrast to existing methods which start with learning from demonstrations (LfD) and then use…
This paper proposes an improvement to the existing data-driven Neural Belief Tracking (NBT) framework for Dialogue State Tracking (DST). The existing NBT model uses a hand-crafted belief state update mechanism which involves an expensive…
Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsity and overfitting,…
Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the…
Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is…
Existing approaches to dialogue state tracking rely on pre-defined ontologies consisting of a set of all possible slot types and values. Though such approaches exhibit promising performance on single-domain benchmarks, they suffer from…
The MultiWOZ 2.0 dataset has greatly boosted the research on dialogue state tracking (DST). However, substantial noise has been discovered in its state annotations. Such noise brings about huge challenges for training DST models robustly.…
Curriculum learning (CL) aims to increase the performance of a learner on a given task by applying a specialized learning strategy. This strategy focuses on either the dataset, the task, or the model. There is little to no work analysing…
Recent multimodal large language models (MLLMs) perform strongly on general visual understanding, diagram and chart reasoning, and document-centric perception. However, these abilities are learned from heterogeneous supervision sources with…
A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and…
ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing performance, ELECTRA still faces the challenges of monotonous…
Sequence labeling models often benefit from incorporating external knowledge. However, this practice introduces data heterogeneity and complicates the model with additional modules, leading to increased expenses for training a…
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…
Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems. An example is the frame tracking task, which requires recording multiple frames, one for each user goal set during the dialogue. This allows a…
Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search…
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…
The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction…
A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge. However, current methods for Continual Dialogue State Tracking (DST), a crucial function of…