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 …

Industry scale semi-supervised learning for natural language understanding

L Chen, F Garcia, V Kumar, H **e, J Lu - arxiv preprint arxiv:2103.15871, 2021‏ - arxiv.org
This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the
student-teacher framework, which leverages millions of unlabeled examples to improve …

A closer look at feature space data augmentation for few-shot intent classification

V Kumar, H Glaude, C De Lichy… - arxiv preprint arxiv …, 2019‏ - arxiv.org
New conversation topics and functionalities are constantly being added to conversational AI
agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable …

Transfer learning-based query classification for intelligent building information spoken dialogue

N Wang, RRA Issa, CJ Anumba - Automation in Construction, 2022‏ - Elsevier
Retrieving queried information from building information models (BIM) requires experience
in structured query languages and manipulation of BIM software. Artificial Intelligence (AI) …

Data augmentation for spoken language understanding via pretrained language models

B Peng, C Zhu, M Zeng, J Gao - arxiv preprint arxiv:2004.13952, 2020‏ - arxiv.org
The training of spoken language understanding (SLU) models often faces the problem of
data scarcity. In this paper, we put forward a data augmentation method using pretrained …

Semi-supervised self-learning for arabic hate speech detection

S Alsafari, S Sadaoui - 2021 IEEE International Conference on …, 2021‏ - ieeexplore.ieee.org
One key for improving hate speech detection performance is to have a textual training
corpus that is vast and confidently labeled. This paper develops a semi-supervised learning …

Smart chatbot for user authentication

P Voege, IIM Abu Sulayman, A Ouda - Electronics, 2022‏ - mdpi.com
Despite being the most widely used authentication mechanism, password-based
authentication is not very secure, being easily guessed or brute-forced. To address this …

A Semi-Supervised Approach for Identifying Cyberbullying Text in Bangla Language

A Faruque, HA Mustafa - 2024 6th International Conference on …, 2024‏ - ieeexplore.ieee.org
Social media has become increasingly popular, and it is now relatively simple to
communicate with people online. As a result, there is more hate speech directed at specific …

Feature based sentimental analysis for prediction of mobile reviews using hybrid bag-boost algorithm

SK Pathuri, N Anbazhagan… - 2020 7th International …, 2020‏ - ieeexplore.ieee.org
Sentiment analysis or opinion mining is one of the major challenge of NLP (natural
language processing). Business Analytics plays a key role in the current scenario with a …

[HTML][HTML] The Impact of COVID-19 on 'Spanish-Speaking'Children's Phonological Development

M Acero-Ferrero, R Lozano-Blasco, MJC Moreno… - Education …, 2024‏ - mdpi.com
Communication and social interaction have been limited during the COVID-19 pandemic.
The aim of this study was to check if 3-, 4-, and 5-year-old children manifest alterations in …