A survey of joint intent detection and slot filling models in natural language understanding
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 …
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 …
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
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 …
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
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 …
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.
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 …
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
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 …
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 …
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
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 …
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
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 …
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 …
utterances, which attracts increasing attention recently. Although current few-shot learning …