paper-with-me

홈 › Papers

Scalable Multi-Domain Dialogue State Tracking

2017-12-29 · Abhinav Rastogi, Dilek Hakkani-Tur, Larry Heck

Dialogue state tracking (DST) is a key component of task-oriented dialogue systems. DST estimates the user's goal at each user turn given the interaction until then. State of the art approaches for state tracking rely on deep learning methods, and represent dialogue state as a distribution over all possible slot values for each slot present in the ontology. Such a representation is not scalable when the set of possible values are unbounded (e.g., date, time or location) or dynamic (e.g., movies or usernames). Furthermore, training of such models requires labeled data, where each user turn is annotated with the dialogue state, which makes building models for new domains challenging. In this paper, we present a scalable multi-domain deep learning based approach for DST. We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge. Restricting these candidate sets to be bounded in size addresses the problem of slot-scalability. Furthermore, by leveraging the slot-independent architecture and transfer learning, we show that our proposed approach facilitates quick adaptation to new domains.

📄 PDF Abstract BibTeX arXiv:1712.10224

Code (1)

google-research-datasets/simulated-dialogue 공식 구현

Tasks

Dialogue State TrackingMulti-domain Dialogue State TrackingTask-Oriented Dialogue SystemsTransfer Learning

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

Similar Papers 제목 키워드 기반

The SPPD System for Schema Guided Dialogue State Tracking Challenge

2020-06-16 · Miao Li, Haoqi Xiong, Yunbo Cao

This paper introduces one of our group's work on the Dialog System Technology Challenges 8 (DSTC8), the SPPD system for Schema Guided dialogue state tracking challenge. This challenge, named as Track 4 in DSTC8, provides…

Dialogue State TrackingMulti-domain Dialogue State Tracking

Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT

2024-09-10 · Jihyun Lee, Gary Geunbae Lee

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 l…

AllDialogue State TrackingIn-Context LearningTransfer Learning

Candidate Attended Dialogue State Tracking Using BERT

2026-07-17 · Junyuan Zheng, Onkar Salvi, John Chan arxiv

Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream module…

Task-Oriented Dialogue SystemsZero-shot GeneralizationDialogue State Tracking

Toward Scalable Neural Dialogue State Tracking Model

2018-12-03 · Elnaz Nouri, Ehsan Hosseini-Asl

The latency in the current neural based dialogue state tracking models prohibits them from being used efficiently for deployment in production systems, albeit their highly accurate performance. This paper proposes a new …

Dialogue State TrackingmodelMulti-domain Dialogue State Tracking

Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation

2019-09-02 · IJCNLP 2019 11 · Liliang Ren, Jianmo Ni, Julian McAuley

Existing approaches to dialogue state tracking rely on pre-defined ontologies consisting of a set of all possible slot types and values. Though such approaches exhibit promising performance on single-domain benchmarks, t…

DecoderDialogue State TrackingMulti-domain Dialogue State Tracking