H Liu, G Chen, P Li, P Zhao, X Wu - Neurocomputing, 2021 - Elsevier
… In this paper, we put forward a multi-label textclassification algorithm LELC(jointlearning … to solve the issue of multi-label textclassification with a large number of class labels. …
… learning the representations of text sequences. We propose to view textclassification as a label-word joint … the compatibility of embeddings between text sequences and labels. The …
L Li, H Wang, X Sun, B Chang, S Zhao… - Proceedings of the 2015 …, 2015 - aclanthology.org
… To address this problem, we propose a novel jointlearning algorithm that allows the feedbacks to be propagated from the classifiers for latter labels to the classifier for the current label. …
P Liu, X Qiu, X Huang - arXiv preprint arXiv:1605.05101, 2016 - arxiv.org
… textclassification tasks show that the jointlearning of multiple related tasks together can improve the performance of each task relative to learning … Thus, after the jointlearning phase, …
H Tang, M Li, B Jin - … processing and the 9th international joint …, 2019 - aclanthology.org
… several states of the art models in terms of text perplexity and topic coherence. Moreover, … textclassification task. Finally, given the input texts, our model can generate meaningful texts …
W Li, X Zhu, S Gong - arXiv preprint arXiv:1705.04724, 2017 - arxiv.org
… This further validates the advantages of our jointlearning of multi-loss classification for optimising re-id especially when the re-id test population size increases (751 people on Market-…
… In this paper, we propose a jointlearning approach for sentiment and emotion classification. The basic idea of the approach is to annotate a small size of data where the samples are …
C Zhao, S Wang, D Li - Knowledge-Based Systems, 2020 - Elsevier
… We propose a novel framework with multi-source domain adaptation and jointlearning for multi-source cross-domain sentiment classification tasks This framework uses bi-directional …
L Gui, J Leng, J Zhou, R Xu, Y He - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… 3.2 Neural TextClassification Model For the textclassification model, we use a hierarchical … the jointlearning of topics and sentiment attentions. Another advantage of mutual learning is …