Satellite communication systems operate across diverse orbital configurations and terrestrial environments, where channel characteristics vary significantly due to differences in Doppler shifts, shadow fading, and propagation conditions. This heterogeneity causes severe domain shift, degrading the performance of interference recognition models trained on one channel environment when deployed in another. To address this challenge, this paper proposes a Cross-Domain Adversarial Disentanglement Network (DADN) that explicitly separates interference-invariant features from channel-dependent features through a dual-stream architecture. Unlike conventional domain adaptation methods that perform global feature alignment, DADN employs a parallel dual-stream architecture where the interference feature extractor and channel feature extractor operate independently with separate parameters, enabling explicit separation of transferable semantic information from environment-specific propagation effects.The interference feature extractor learns intrinsic signal characteristics shared across environments, while the channel feature extractor captures environment-specific propagation attributes. A gradient reversal mechanism adversarially removes residual channel information from interference features, and KL-divergence regularization prevents channel features from encoding interference category information, jointly ensuring feature orthogonality. Experiments across four representative satellite scenarios (LEO-Urban, LEO-Open, MEO-Suburban, GEO-Rain) demonstrate that DADN achieves 98.49% average recognition accuracy, outperforming CNN baseline by 2.08%, CLDNN by 1.24%, and DANN by 1.57%. Furthermore, DADN maintains over 97% accuracy with only 5% labeled target-domain data, confirming its strong cross-domain adaptability and data efficiency for practical satellite interference recognition applications.

Stylized Image Captioning aims to generate captions with accurate image content and stylized elements simultaneously. However, large-scaled image and stylized caption pairs cost lots of resources and are usually unavailable. Therefore, it's a challenge to generate stylized captions without paired stylized caption dataset. Previous work on controlling the style of generated captions in an unsupervised way can be divided into two ways: implicitly and explicitly. The former mainly relies on a well-trained language model to capture style knowledge, which is limited to a single style and hard to handle multi-style task. Thus, the latter uses extra style constraints such as outlined style labels or stylized words extracted from stylized sentences to control the style rather than the trained style-specific language model. However, certain styles, such as humorous and romance, are implied in the whole sentence, instead of in some words of a sentence. To address the problems above, we propose a two-step method based on Transformer: firstly detach style representations from large-scaled stylized text-only corpus to provide more holistic style supervision, and secondly attach the style representations to image content to generate stylized captions. We learn a shared image-text space to narrow the gap between the image and the text modality for better attachment. Due to the trade-off between semantics and style, we explore three injection methods of style representations to balance two requirements of image content preservation and stylization. Experiments show that our method outperforms the state-of-the-art systems in overall performance, especially on implied styles.

Word Sense Disambiguation (WSD), as a tough task in Natural Language Processing (NLP), aims to identify the correct sense of an ambiguous word in a given context. There are two mainstreams in WSD. Supervised methods mainly utilize labeled context to train a classifier which generates the right probability distribution of word senses. Meanwhile knowledge-based (unsupervised) methods which focus on glosses (word sense definitions) always calculate the similarity of context-gloss pair as score to find out the right word sense. In this paper, we propose a generative adversarial framework WSD-GAN which combines two mainstream methods in WSD. The generative model, based on supervised methods, tries to generate a probability distribution over the word senses. Meanwhile the discriminative model, based on knowledge-based methods, focuses on predicting the relevancy of the context-gloss pairs and identifies the correct pairs over the others. Furthermore, in order to optimize both two models, we leverage policy gradient to enhance the performances of the two models mutually. Our experimental results show that WSD-GAN achieves competitive results on several English all-words WSD datasets.

In this paper, we focus on the task of finegrained text sentiment transfer (FGST).This task aims to revise an input sequence to satisfy a given sentiment intensity, while preserving the original semantic content.Different from conventional sentiment transfer task that only reverses the sentiment polarity (positive/negative) of text, the FTST task requires more nuanced and fine-grained control of sentiment.To remedy this, we propose a novel Seq2SentiSeq model.Specifically, the numeric sentiment intensity value is incorporated into the decoder via a Gaussian kernel layer to finely control the sentiment intensity of the output.Moreover, to tackle the problem of lacking parallel data, we propose a cycle reinforcement learning algorithm to guide the model training.In this framework, the elaborately designed rewards can balance both sentiment transformation and content preservation, while not requiring any ground truth output.Experimental results show that our approach can outperform existing methods by a large margin in both automatic evaluation and human evaluation.Our code and data, including outputs of all baselines and our model are available at https://github.com/luofuli/ Fine-grained-Sentiment-Transfer. 1