相关论文: Proactive Dialogue Model with Intent Prediction

Though great progress has been made for human-machine conversation, current dialogue system is still in its infancy: it usually converses passively and utters words more as a matter of response, rather than on its own initiatives. In this…

In this paper, we provide an extensive analysis of multi-label intent classification using Large Language Models (LLMs) that are open-source, publicly available, and can be run in consumer hardware. We use the MultiWOZ 2.1 dataset, a…

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small…

Recent advances in video multimodal large language models (Video MLLMs) have significantly enhanced video understanding and multi-modal interaction capabilities. While most existing systems operate in a turn-based manner where the model can…

Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios. While unlike the general…

Recent advances in Multimodal Large Language Models (MLLMs) have driven rapid progress in Vision-Language-Action (VLA) models for robotic manipulation. Although effective in many scenarios, current approaches largely rely on explicit…

Building conversational systems in new domains and with added functionality requires resource-efficient models that work under low-data regimes (i.e., in few-shot setups). Motivated by these requirements, we introduce intent detection…

Goal-directed dialogue systems aim to proactively reach a pre-determined target through multi-turn conversations. The key to achieving this task lies in planning dialogue paths that smoothly and coherently direct conversations towards the…

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next…

Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. Although adept at devising strategies and performing tasks, these agents…

Intent detection is a key component of modern goal-oriented dialog systems that accomplish a user task by predicting the intent of users' text input. There are three primary challenges in designing robust and accurate intent detection…

In a conversation or a dialogue process, attention and intention play intrinsic roles. This paper proposes a neural network based approach that models the attention and intention processes. It essentially consists of three recurrent…

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…

Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, despite their impressive capabilities, they still possess limitations,…

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without…

Task-oriented dialogue (TOD) systems are commonly designed with the presumption that each utterance represents a single intent. However, this assumption may not accurately reflect real-world situations, where users frequently express…

Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking…

Turn-taking, aiming to decide when the next speaker can start talking, is an essential component in building human-robot spoken dialogue systems. Previous studies indicate that multimodal cues can facilitate this challenging task. However,…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Proactive dialogue system is able to lead the conversation to a goal topic and has advantaged potential in bargain, persuasion and negotiation. Current corpus-based learning manner limits its practical application in real-world scenarios.…