yutongli18 Goto Github PK

bert-dst

BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer

coco-dst

基于 MultiWOZ 数据集生成反事实，检测 DST 模型的鲁棒性。

dicos-master

DiCoS

domainaware_dst

[25]多领域对话系统的领域感知对话状态跟踪器

ds2

对话摘要作为对话状态（DS2），用于少样本对话状态跟踪的模板引导摘要

dst-as-prompting

[19]使用模式驱动提示语言模型的对话状态跟踪

dst-metaassist

MetaASSIST

dst-star

Slot Self-Attentive Dialogue State Tracking

few-shot-dst

使用元学习的少样本对话状态跟踪

ic-dst

Code base of In-Context Learning for Dialogue State tracking

javatemplate

Java设计模式

leetcode2023

msp

[27] 通过继承槽池中的槽值来跟踪对话状态

multiwoz

MultiWOZ Dataset

multiwoz2.4

MultiWOZ 2.4

nadst

[26] 非自回归对话状态跟踪

savn

[36]SAVN

sgd

The Schema-Guided Dialogue Dataset

sm-dst

[29]

toatod

[37]Task-Optimized Adapters for an End-to-End Dialogue System Paper Code

trade-dst

[30] TRADE

zero-shot-dst

[31]跨任务迁移的零样本对话状态跟踪

zero-shot-multiwoz-acl2020

[32]Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking