Related papers: Diversifying Topic-Coherent Response Generation fo…

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to a multi-turn dialogue scenario by modifying the state-of-the-art hredGAN architecture to simultaneously capture utterance…

Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc.…

The generation of personalized dialogue is vital to natural and human-like conversation. Typically, personalized dialogue generation models involve conditioning the generated response on the dialogue history and a representation of the…

For the field of education, being able to generate semantically correct and educationally relevant multiple choice questions (MCQs) could have a large impact. While question generation itself is an active research topic, generating…

Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture to produce better responses but pay little attention to…

Understanding how the brain responds to sensory inputs is challenging: brain recordings are partial, noisy, and high dimensional; they vary across sessions and subjects and they capture highly nonlinear dynamics. These challenges have led…

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

We propose an approach to referring expression generation (REG) in visually grounded dialogue that is meant to produce referring expressions (REs) that are both discriminative and discourse-appropriate. Our method constitutes a two-stage…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or…

Grounding dialogue system with external knowledge is a promising way to improve the quality of responses. Most existing works adopt knowledge graphs (KGs) as the external resources, paying attention to the contribution of entities in the…

Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue…

Retrieval-augmented generation (RAG) systems rely on accurate document retrieval to ground large language models (LLMs) in external knowledge, yet retrieval quality often degrades in corpora where topics overlap and thematic variation is…

Timeline Generation aims at summarizing news from different epochs and telling readers how an event evolves. It is a new challenge that combines salience ranking with novelty detection. For long-term public events, the main topic usually…

We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with…

Recently, denoising diffusion probabilistic models and generative score matching have shown high potential in modelling complex data distributions while stochastic calculus has provided a unified point of view on these techniques allowing…

Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the internal knowledge…

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model…