Related papers: Non-Autoregressive Dialog State Tracking
Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems. Since dialogue management requires to have access to not only…
Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consistency and scalability. As conversations lengthen, essential information becomes sparse and…
Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…
The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…
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…
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…
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…
As a key component in a dialogue system, dialogue state tracking plays an important role. It is very important for dialogue state tracking to deal with the problem of unknown slot values. As far as we known, almost all existing approaches…
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-level augmentation…
Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference…
Slot filling is identifying contiguous spans of words in an utterance that correspond to certain parameters (i.e., slots) of a user request/query. Slot filling is one of the most important challenges in modern task-oriented dialog systems.…
Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset. In this paper, we propose to use curriculum learning (CL) to better leverage both the…
MultiWOZ is one of the most popular multi-domain task-oriented dialog datasets, containing 10K+ annotated dialogs covering eight domains. It has been widely accepted as a benchmark for various dialog tasks, e.g., dialog state tracking…
Dialogue state tracking (DST) is evaluated by exact matching methods, which rely on large amounts of labeled data and ignore semantic consistency, leading to over-evaluation. Currently, leveraging large language models (LLM) in evaluating…
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…
Though Dialogue State Tracking (DST) is a core component of spoken dialogue systems, recent work on this task mostly deals with chat corpora, disregarding the discrepancies between spoken and written language.In this paper, we propose…
Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. However, their effectiveness in task-oriented dialogues (TOD), which…
A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also…
Dialogue state tracking plays a crucial role in extracting information in task-oriented dialogue systems. However, preceding research are limited to textual modalities, primarily due to the shortage of authentic human audio datasets. We…
Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state…