Recent advances in deep learning based dialogue systems: A systematic survey

J Ni, T Young, V Pandelea, F Xue… - Artificial intelligence review, 2023 - Springer
Dialogue systems are a popular natural language processing (NLP) task as it is promising in
real-life applications. It is also a complicated task since many NLP tasks deserving study are …

Neural approaches to conversational AI

J Gao, M Galley, L Li - The 41st international ACM SIGIR conference on …, 2018 - dl.acm.org
This tutorial surveys neural approaches to conversational AI that were developed in the last
few years. We group conversational systems into three categories:(1) question answering …

Few-shot slot tagging with collapsed dependency transfer and label-enhanced task-adaptive projection network

Y Hou, W Che, Y Lai, Z Zhou, Y Liu, H Liu… - arxiv preprint arxiv …, 2020 - arxiv.org
In this paper, we explore the slot tagging with only a few labeled support sentences (aka few-
shot). Few-shot slot tagging faces a unique challenge compared to the other few-shot …

Recent neural methods on slot filling and intent classification for task-oriented dialogue systems: A survey

S Louvan, B Magnini - arxiv preprint arxiv:2011.00564, 2020 - arxiv.org
In recent years, fostered by deep learning technologies and by the high demand for
conversational AI, various approaches have been proposed that address the capacity to …

Low-resource domain adaptation for compositional task-oriented semantic parsing

X Chen, A Ghoshal, Y Mehdad, L Zettlemoyer… - arxiv preprint arxiv …, 2020 - arxiv.org
Task-oriented semantic parsing is a critical component of virtual assistants, which is
responsible for understanding the user's intents (set reminder, play music, etc.). Recent …

Coach: A coarse-to-fine approach for cross-domain slot filling

Z Liu, GI Winata, P Xu, P Fung - arxiv preprint arxiv:2004.11727, 2020 - arxiv.org
As an essential task in task-oriented dialog systems, slot filling requires extensive training
data in a certain domain. However, such data are not always available. Hence, cross …

Robust zero-shot cross-domain slot filling with example values

DJ Shah, R Gupta, AA Fayazi… - arxiv preprint arxiv …, 2019 - arxiv.org
Task-oriented dialog systems increasingly rely on deep learning-based slot filling models,
usually needing extensive labeled training data for target domains. Often, however, little to …

Augmented natural language for generative sequence labeling

B Athiwaratkun, CN Santos, J Krone… - arxiv preprint arxiv …, 2020 - arxiv.org
We propose a generative framework for joint sequence labeling and sentence-level
classification. Our model performs multiple sequence labeling tasks at once using a single …

How does the combined risk affect the performance of unsupervised domain adaptation approaches?

L Zhong, Z Fang, F Liu, J Lu, B Yuan… - Proceedings of the AAAI …, 2021 - ojs.aaai.org
Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples
from the source domain and unlabeled samples from the target domain. Classical UDA …

Generative zero-shot prompt learning for cross-domain slot filling with inverse prompting

X Li, L Wang, G Dong, K He, J Zhao, H Lei… - arxiv preprint arxiv …, 2023 - arxiv.org
Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source
domain to the unlabeled target domain. Existing models either encode slot descriptions and …