相关论文: Diverse Retrieval-Augmented In-Context Learning fo…

Few-shot Continual Relation Extraction is a crucial challenge for enabling AI systems to identify and adapt to evolving relationships in dynamic real-world domains. Traditional memory-based approaches often overfit to limited samples,…

Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging…

Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a new pre-trained model specifically designed for…

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's requests (\textit{a.k.a} dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform this update in three…

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent throughout the conversation. State-of-the-art DST models are typically trained in a supervised manner…

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting,…

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined…

Task-oriented dialogue systems aim to help users achieve their goals in specific domains. Recent neural dialogue systems use the entire dialogue history for abundant contextual information accumulated over multiple conversational turns.…

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence…

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data…

The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a…

An important yet rarely tackled problem in dialogue state tracking (DST) is scalability for dynamic ontology (e.g., movie, restaurant) and unseen slot values. We focus on a specific condition, where the ontology is unknown to the state…

The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority…

In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of…

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their…

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

Dialogue state tracking (DST) is a component of the task-oriented dialogue system. It is responsible for extracting and managing slot values according to dialogue utterances, where each slot represents an essential part of the information…

Ranking responses for a given dialogue context is a popular benchmark in which the setup is to re-rank the ground-truth response over a limited set of $n$ responses, where $n$ is typically 10. The predominance of this setup in conversation…

Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from…

Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the…