A survey of joint intent detection and slot filling models in natural language understanding

H Weld, X Huang, S Long, J Poon, SC Han - ACM Computing Surveys, 2022 - dl.acm.org
Intent classification, to identify the speaker's intention, and slot filling, to label each token
with a semantic type, are critical tasks in natural language understanding. Traditionally the …

Revisiting mahalanobis distance for transformer-based out-of-domain detection

A Podolskiy, D Lipin, A Bout, E Artemova… - Proceedings of the …, 2021 - ojs.aaai.org
Real-life applications, heavily relying on machine learning, such as dialog systems, demand
for out-of-domain detection methods. Intent classification models should be equipped with a …

Synergizing large language models and pre-trained smaller models for conversational intent discovery

J Liang, L Liao, H Fei, J Jiang - Findings of the Association for …, 2024 - aclanthology.org
Abstract In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle
with overfitting to familiar intents and fail to label newly discovered ones. This issue stems …

Multi-level knowledge distillation for out-of-distribution detection in text

Q Wu, H Jiang, H Yin, BF Karlsson, CY Lin - arXiv preprint arXiv …, 2022 - arxiv.org
Self-supervised representation learning has proved to be a valuable component for out-of-
distribution (OoD) detection with only the texts of in-distribution (ID) examples. These …

[PDF][PDF] Out-of-Scope Intent Detection on A Knowledge-Based Chatbot.

LP Manik, Z Akbar, HF Mustika, A Indrawati… - International Journal of …, 2021 - inass.org
Knowledge-based chatbot (KBC) has grown in popularity in recent years and has been
widely used for various use cases. Building KBC from scratch using deep learning (DL) is …

A simple meta-learning paradigm for zero-shot intent classification with mixture attention mechanism

H Liu, S Zhao, X Zhang, F Zhang, J Sun, H Yu… - Proceedings of the 45th …, 2022 - dl.acm.org
Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims
to deal with numerous fast-emerging unacquainted intents without annotated training data …

A hybrid architecture for out of domain intent detection and intent discovery

M Akbari, A Mohades, MH Shirali-Shahreza - arXiv preprint arXiv …, 2023 - arxiv.org
Intent Detection is one of the tasks of the Natural Language Understanding (NLU) unit in
task-oriented dialogue systems. Out of Scope (OOS) and Out of Domain (OOD) inputs may …

Did you ask a good question? a cross-domain question intention classification benchmark for text-to-sql

Y Zhang, X Dong, S Chang, T Yu, P Shi… - arXiv preprint arXiv …, 2020 - arxiv.org
Neural models have achieved significant results on the text-to-SQL task, in which most
current work assumes all the input questions are legal and generates a SQL query for any …

D2U: distance-to-uniform learning for out-of-scope detection

E Yilmaz, C Toraman - Proceedings of the 2022 conference of the …, 2022 - aclanthology.org
Supervised training with cross-entropy loss implicitly forces models to produce probability
distributions that follow a discrete delta distribution. Model predictions in test time are …

Boosting few-shot intent detection via feature enrichment and regularization

F Zhang, W Chen, P Zhao, T Wang - Neurocomputing, 2024 - Elsevier
Few-shot intent detection aims to detect fast-emerging new intents from limited labeled
utterances, which attracts increasing attention recently. Although current few-shot learning …