Attention, please! A survey of neural attention models in deep learning

A de Santana Correia, EL Colombini - Artificial Intelligence Review, 2022 - Springer
In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …

[HTML][HTML] A methodological approach to enable natural language interaction in an Intelligent Tutoring System

P Arnau-González, M Arevalillo-Herráez… - Computer Speech & …, 2023 - Elsevier
In this paper, we present and evaluate the recent incorporation of a conversational agent
into an Intelligent Tutoring System (ITS), using the open-source machine learning framework …

Convolutional residual‐attention: A deep learning approach for precipitation nowcasting

Q Yan, F Ji, K Miao, Q Wu, Y **a… - Advances in Meteorology, 2020 - Wiley Online Library
Short‐term precipitation forecast in local areas based on radar reflectance images has
become a hot spot issue in the meteorological field, which has an important impact on daily …

I-BERT: Inductive Generalization of Transformer to Arbitrary Context Lengths

H Nam, SB Seo, VS Mailthody, N Michael… - arxiv preprint arxiv …, 2020 - arxiv.org
Self-attention has emerged as a vital component of state-of-the-art sequence-to-sequence
models for natural language processing in recent years, brought to the forefront by pre …

Study on a prediction model of superhighway fuel consumption based on the test of easy car platform

YM He, J Kang, YL Pei, B Ran, YT Song - Sustainability, 2020 - mdpi.com
To explore the relationship between fuel consumption and speed for a vehicle on a
superhighway with a design speed exceeding 120 km/h, the fuel consumption data provided …

A corpus augmentation approach for improving the performance of dialogue systems in the Greek language

I Loumiotis, G Petasis - 11th Hellenic Conference on Artificial …, 2020 - dl.acm.org
One of the main challenges in dialogue systems is their efficiency when trained with small
corpora. Although this problem has been solved for dialogue systems in the English …

[PDF][PDF] Leveraging Speaker Profile and Knowledge Enrichment for End-to-End Advising Response Ranking

SP Chang, YN Chen, TR Chiang, CW Huang - 2020 - joshchang1112.github.io
Retrieval-based dialogue modeling has drawn a lot of attention due to its practical usage.
Also, different speakers may have diverse preferences and play different roles, so modeling …

Injecting Hierarchy with U-Net Transformers

D Donahue, V Lialin, A Rumshisky - arxiv preprint arxiv:1910.10488, 2019 - arxiv.org
The Transformer architecture has become increasingly popular over the past two years,
owing to its impressive performance on a number of natural language processing (NLP) …

[PDF][PDF] Neural Methods for Sentiment Analysis and Text Summarization

TH Le - 2020 - docnum.univ-lorraine.fr
Nowadays, we are living in the age of intelligent machines. It's hard to ignore because they
appear everywhere, either in the form of a physical robots, virtual assistants or autonomous …