Content-based and knowledge-enriched representations for classification across modalities: a survey
N Pittaras, G Giannakopoulos, P Stamatopoulos… - ACM Computing …, 2023 - dl.acm.org
This survey documents representation approaches for classification across different
modalities, from purely content-based methods to techniques utilizing external sources of …
modalities, from purely content-based methods to techniques utilizing external sources of …
Synergizing machine learning & symbolic methods: A survey on hybrid approaches to natural language processing
R Panchendrarajan, A Zubiaga - Expert Systems with Applications, 2024 - Elsevier
The advancement of machine learning and symbolic approaches have underscored their
strengths and weaknesses in Natural Language Processing (NLP). While machine learning …
strengths and weaknesses in Natural Language Processing (NLP). While machine learning …
Unsupervised cross-domain rumor detection with contrastive learning and cross-attention
H Ran, C Jia - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Massive rumors usually appear along with breaking news or trending topics, seriously
hindering the truth. Existing rumor detection methods are mostly focused on the same …
hindering the truth. Existing rumor detection methods are mostly focused on the same …
Towards Distribution-shift Robust Text Classification of Emotional Content
Supervised models based on Transformers have been shown to achieve impressive
performances in many natural language processing tasks. However, besides requiring a …
performances in many natural language processing tasks. However, besides requiring a …
Automatic domain classification of text using machine learning
MA Tayal, V Bajaj, A Gore, P Yadav… - … , Circuits, and Systems …, 2023 - ieeexplore.ieee.org
The exponential growth of data in recent years has presented a challenge in extracting
insights due to its unstructured nature. Efficient management of this vast information requires …
insights due to its unstructured nature. Efficient management of this vast information requires …
Label-aware learning to enhance unsupervised cross-domain rumor detection
H Ran, X Li, Z Zhang - Journal of Network and Computer Applications, 2025 - Elsevier
Recently, massive research has achieved significant development in improving the
performance of rumor detection. However, identifying rumors in an invisible domain is still an …
performance of rumor detection. However, identifying rumors in an invisible domain is still an …
Knowledge-aware interaction networks for domain-adaptive end-to-end aspect-based sentiment analysis
B Lin, Z Lin, F Li, Z Liang, Z Lu, Y Xue - International Journal of Machine …, 2024 - Springer
Great efforts have been made toward leveraging unsupervised domain adaptation
techniques in end-to-end aspect-based sentiment analysis (E2E ABSA), to overcome the …
techniques in end-to-end aspect-based sentiment analysis (E2E ABSA), to overcome the …
[图书][B] Hardware-Aware Efficient Deep Learning
Z Dong - 2022 - search.proquest.com
Significant improvements in the accuracy of Neural Networks (NNs) have been observed for
a wide range of problems, often achieved by highly over-parameterized models. Despite the …
a wide range of problems, often achieved by highly over-parameterized models. Despite the …
Implementation of Domain Adaptation for Keyword Determination of Scientific Articles Based on Multilabel BERT
S Rafif, RS Perdana - Proceedings of the 8th International Conference …, 2023 - dl.acm.org
Keywords that are not properly determined make scientific articles unreachable by readers.
The process of determining keywords done manually can cause errors and can waste time …
The process of determining keywords done manually can cause errors and can waste time …