Related papers: Long-term Control for Dialogue Generation: Methods…

Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or…

Controllable text generation is a growing field within natural language generation (NLG) that focuses on producing text that meets specific constraints in real-world applications. Previous approaches, such as plug-and-play controllers…

Human ratings are one of the most prevalent methods to evaluate the performance of natural language processing algorithms. Similarly, it is common to measure the quality of sentences generated by a natural language generation model using…

LLMs are not generally able to adjust the length of their outputs based on strict length requirements, a capability that would improve their usefulness in applications that require adherence to diverse user and system requirements. We…

Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their…

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…

In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via…

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models…

Though generative dialogue modeling is widely seen as a language modeling task, the task demands an agent to have a complex natural language understanding of its input text to carry a meaningful interaction with an user. The automatic…

Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to…

Large Language Models (LLMs) demonstrate superior performance in generative scenarios and have attracted widespread attention. Among them, stylized dialogue generation is essential in the context of LLMs for building intelligent and…

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…

Automatic metrics are extensively used to evaluate natural language processing systems. However, there has been increasing focus on how they are used and reported by practitioners within the field. In this paper, we have conducted a survey…

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role…

We present a general approach towards controllable societal biases in natural language generation (NLG). Building upon the idea of adversarial triggers, we develop a method to induce societal biases in generated text when input prompts…

In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent…

Maintaining semantic consistency over extended text sequences remains a fundamental challenge in long-form text generation, where conventional training methodologies often struggle to prevent contextual drift and coherence degradation. A…

The rapid development of the Internet has profoundly changed human life. Humans are increasingly expressing themselves and interacting with others on social media platforms. However, although artificial intelligence technology has been…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains…