Related papers: Cascaded LSTMs based Deep Reinforcement Learning f…

Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information. To address this limitation, in this paper, we propose the Self-Controlled Memory (SCM)…

Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions…

Dialogue systems have long supported learner reflections, with theoretically grounded, rule-based designs offering structured scaffolding but often struggling to respond to shifts in engagement. Large Language Models (LLMs), in contrast,…

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue. Existing approaches to DA classification model utterances without incorporating the turn changes among speakers…

Time series prediction can be generalized as a process that extracts useful information from historical records and then determines future values. Learning long-range dependencies that are embedded in time series is often an obstacle for…

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and…

With the significant progress of speech technologies, spoken goal-oriented dialogue systems are becoming increasingly popular. One of the main modules of a dialogue system is typically the dialogue policy, which is responsible for…

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant…

Long-term memory (LTM) is essential for large language models (LLMs) to achieve autonomous intelligence in complex, evolving environments. Despite increasing efforts in memory-augmented and retrieval-based architectures, there remains a…

Reinforcement learning (RL) has emerged as a powerful approach for tackling complex medical decision-making problems such as treatment planning, personalized medicine, and optimizing the scheduling of surgeries and appointments. It has…

Dialogue state modules are a useful component in a task-oriented dialogue system. Traditional methods find dialogue states by manually labeling training corpora, upon which neural models are trained. However, the labeling process can be…

Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in…

We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances…

Most human interactions occur in the form of spoken conversations where the semantic meaning of a given utterance depends on the context. Each utterance in spoken conversation can be represented by many semantic and speaker attributes, and…

Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage the power of…

Efficient Multimodal Large Language Models (EMLLMs) can improve performance through Chain-of-Thought (CoT) reasoning, but they have poor self-evaluation capabilities during the CoT reasoning process. This is due to their tendency to…

Stacking non-linear layers allows deep neural networks to model complicated functions, and including residual connections in Transformer layers is beneficial for convergence and performance. However, residual connections may make the model…

Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time.…

Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues can attributed to reasons including (1) short-range model architectures…