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 …
Transfer learning: Survey and classification
A key notion in numerous data mining and machine learning (ML) algorithms says that the
training data and testing data are essentially in the similar feature space and also have the …
training data and testing data are essentially in the similar feature space and also have the …
Recent neural methods on slot filling and intent classification for task-oriented dialogue systems: A survey
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 …
conversational AI, various approaches have been proposed that address the capacity to …
Multitask learning for multilingual intent detection and slot filling in dialogue systems
Dialogue systems are becoming an ubiquitous presence in our everyday lives having a
huge impact on business and society. Spoken language understanding (SLU) is the critical …
huge impact on business and society. Spoken language understanding (SLU) is the critical …
Robust zero-shot cross-domain slot filling with example values
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 …
usually needing extensive labeled training data for target domains. Often, however, little to …
Cm-net: A novel collaborative memory network for spoken language understanding
Spoken Language Understanding (SLU) mainly involves two tasks, intent detection and slot
filling, which are generally modeled jointly in existing works. However, most existing models …
filling, which are generally modeled jointly in existing works. However, most existing models …
Augmented natural language for generative sequence labeling
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 …
classification. Our model performs multiple sequence labeling tasks at once using a single …
Midas: A dialog act annotation scheme for open domain human machine spoken conversations
Dialog act prediction is an essential language comprehension task for both dialog system
building and discourse analysis. Previous dialog act schemes, such as SWBD-DAMSL, are …
building and discourse analysis. Previous dialog act schemes, such as SWBD-DAMSL, are …
Natural language understanding approaches based on joint task of intent detection and slot filling for IoT voice interaction
Abstract Internet of Things (IoT) based voice interaction system, as a new artificial
intelligence application, provides a new human–computer interaction mode. The more …
intelligence application, provides a new human–computer interaction mode. The more …
CTRAN: CNN-transformer-based network for natural language understanding
M Rafiepour, JS Sartakhti - Engineering Applications of Artificial …, 2023 - Elsevier
Intent-detection (ID) and slot-filling (SF) are fundamental tasks for natural language
understanding. This study introduces a new encoder–decoder CNN-Transformer-based …
understanding. This study introduces a new encoder–decoder CNN-Transformer-based …