Related papers: Sequential Latent Knowledge Selection for Knowledg…
Dialogue structure discovery is essential in dialogue generation. Well-structured topic flow can leverage background information and predict future topics to help generate controllable and explainable responses. However, most previous work…
Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completion rates in extended conversations. To address this…
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…
Implicit discourse relation recognition is a crucial component for automatic discourselevel analysis and nature language understanding. Previous studies exploit discriminative models that are built on either powerful manual features or deep…
We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the `boring output' issue of deterministic dialogue models. Experiments show that our model generates more…
Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…
Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn…
Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context. The existing works…
Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and…
The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters. In this work, we ask a different question: Can multimodal transformers leverage explicit…
Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this…
Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (\emph{e.g.}, knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and…
Dialogue response selection is an important part of Task-oriented Dialogue Systems (TDSs); it aims to predict an appropriate response given a dialogue context. Obtaining key information from a complex, long dialogue context is challenging,…
We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks…
Sequential recommender systems predict items that may interest users by modeling their preferences based on historical interactions. Traditional sequential recommendation methods rely on capturing implicit collaborative filtering signals…
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training. In this work, we explore the challenging task with…
Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come…
Several recent efforts have been devoted to enhancing pre-trained language models (PLMs) by utilizing extra heterogeneous knowledge in knowledge graphs (KGs) and achieved consistent improvements on various knowledge-driven NLP tasks.…
Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and…
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…