相关论文: ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Ze…
This paper explores SynTOD, a new synthetic data generation approach for developing end-to-end Task-Oriented Dialogue (TOD) Systems capable of handling complex tasks such as intent classification, slot filling, conversational…
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from…
Many reasoning techniques for large multimodal models adapt language model approaches, such as Chain-of-Thought (CoT) prompting, which express reasoning as word sequences. While effective for text, these methods are suboptimal for…
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…
Large Language Model (LLM)-based agents have significantly impacted Task-Oriented Dialog Systems (TODS) but continue to face notable performance challenges, especially in zero-shot scenarios. While prior work has noted this performance gap,…
Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain…
In schema-guided dialogue state tracking models estimate the current state of a conversation using natural language descriptions of the service schema for generalization to unseen services. Prior generative approaches which decode slot…
Planning is one of the most critical tasks in autonomous systems, where even a small error can lead to major failures or million-dollar losses. Current state-of-the-art neural planning approaches struggle with complex domains, producing…
The automated generation of layouts is vital for embodied intelligence and autonomous systems, supporting applications from virtual environment construction to home robot deployment. Current approaches, however, suffer from spatial…
Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…
Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD),…
While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate…
Zero-shot slot filling is a well-established subtask of Natural Language Understanding (NLU). However, most existing methods primarily focus on single-turn text data, overlooking the unique complexities of conversational dialogue.…
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of…
Recent advances in neural approaches greatly improve task-oriented dialogue (TOD) systems which assist users to accomplish their goals. However, such systems rely on costly manually labeled dialogs which are not available in practical…
The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates…
To facilitate zero-shot generalization in taskoriented dialog, this paper proposes Language Models as Data (LAD). LAD is a paradigm for creating diverse and accurate synthetic data which conveys the necessary structural constraints and can…
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…
In this work, we approach spoken Dialogue State Tracking (DST) by bridging the representation spaces of speech encoders and LLMs via a small connector module, with a focus on fully open-sourced and open-data components (WavLM-large, OLMo).…
Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language…