Related papers: Topic-aware Pointer-Generator Networks for Summari…

Neural models have recently been used in text summarization including headline generation. The model can be trained using a set of document-headline pairs. However, the model does not explicitly consider topical similarities and differences…

Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented…

Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…

Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word…

The conversational search paradigm introduces a step change over the traditional search paradigm by allowing users to interact with search agents in a multi-turn and natural fashion. The conversation flows naturally and is usually centered…

Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years. The duration of gaps between conversations dictates which topics are relevant and which…

Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task explores how a system connects two topics in a cooperative and coherent manner. The goal of the task is to…

We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap…

Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords, and utterance-level meaning. Feature transitions between utterances occur naturally. However, existing approaches fail to perceive the transitions…

Conversational AI assistants are becoming popular and question-answering is an important part of any conversational assistant. Using relevant utterances as features in question-answering has shown to improve both the precision and recall…

Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained…

Some exciting new approaches to neural architectures for the analysis of conversation have been introduced over the past couple of years. These include neural architectures for detecting emotion, dialogue acts, and sentiment polarity. They…

Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…

Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information…

Context information around words helps in determining their actual meaning, for example "networks" used in contexts of artificial neural networks or biological neuron networks. Generative topic models infer topic-word distributions, taking…

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our…

In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level…

Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This…

In a world of proliferating data, the ability to rapidly summarize text is growing in importance. Automatic summarization of text can be thought of as a sequence to sequence problem. Another area of natural language processing that solves a…

Steady progress has been made in abstractive summarization with attention-based sequence-to-sequence learning models. In this paper, we propose a new decoder where the output summary is generated by conditioning on both the input text and…