Related papers: Conditioned Query Generation for Task-Oriented Dia…
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data…
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…
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with…
Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data…
Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…
Recent advancements in conversational systems have significantly enhanced human-machine interactions across various domains. However, training these systems is challenging due to the scarcity of specialized dialogue data. Traditionally,…
In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that…
Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat…
Text-based audio generation models have limitations as they cannot encompass all the information in audio, leading to restricted controllability when relying solely on text. To address this issue, we propose a novel model that enhances the…
Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the…
With a growing need for robust and general discourse structures in many downstream tasks and real-world applications, the current lack of high-quality, high-quantity discourse trees poses a severe shortcoming. In order the alleviate this…
Current approaches for controlling dialogue response generation are primarily focused on high-level attributes like style, sentiment, or topic. In this work, we focus on constrained long-term dialogue generation, which involves more…
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…
We present an empirical investigation of pre-trained Transformer-based auto-regressive language models for the task of open-domain dialogue generation. Training paradigm of pre-training and fine-tuning is employed to conduct the parameter…
Dialogue systems are usually categorized into two types, open-domain and task-oriented. The first one focuses on chatting with users and making them engage in the conversations, where selecting a proper topic to fit the dialogue context is…
We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The…
Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…
Conversational Tree Search (V\"ath et al., 2023) is a recent approach to controllable dialog systems, where domain experts shape the behavior of a Reinforcement Learning agent through a dialog tree. The agent learns to efficiently navigate…
We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…
In this paper, we focus on task-specific question answering (QA). To this end, we introduce a method for generating exhaustive and high-quality training data, which allows us to train compact (e.g., run on a mobile device), task-specific QA…