Search

Cross-lingual text summarization is a highly desired service for overseas report editing tasks and is formulated in a distributed application to facilitate the cooperation of editors. The multilanguage pre-trained language model (MPLM) can generate high-quality cross-lingual text summaries with simple fine-tuning. However, the MPLM does not adapt to complex variations, like the word order and tense in different languages. When the model performs on these languages with separate syntactic structures and vocabulary morphologies, it will lead to the low-level quality of the cross-lingual summary. The matter worsens when the cross-lingual summarization datasets are low-resource. We use a knowledge distillation framework for the cross-lingual summarization task to address the above issues. By learning the monolingual teacher model, the cross-lingual student model can effectively capture the differences between languages. Since the teacher and student models generate summaries in two languages, their representations lie on different vector spaces. In order to construct representation relationships across languages, we further propose a similarity metric, which is based on bidirectional semantic alignment, to map different language representations to the same space. In order to improve the quality of cross-lingual summaries further, we use contrastive learning to make the student model focus on the differentials among languages. Contrastive learning can enhance the ability of the similarity metric for bidirectional semantic alignment. Our experiments show that our approach is competitive in low-resource scenarios on cross-language summarization datasets in pairs of distant languages. [ABSTRACT FROM AUTHOR]

Multimodal abstractive summarisation (MAS) aims to generate a textual summary from multimodal data collection, such as video‐text pairs. Despite the success of recent work, the existing methods lack a thorough analysis for consistency across multimodal data. Besides, previous work relies on the fusion method to extract multimodal semantics, neglecting the constraints for complementary semantics of each modality. To address those issues, a multilayer cross‐fusion model with the reconstructor for the MAS task is proposed. Their model could thoroughly conduct cross‐fusion for each modality via layers of cross‐modal transformer blocks, resulting in cross‐modal fusion representations with consistency across modalities. Then the reconstructor is employed to reproduce source modalities based on cross‐modal fusion representations. The reconstruction process constrains the fusion representations with the complementary semantics of each modality. Comprehensive comparison and ablation experiments on the open domain multimodal dataset How2 are proposed. The results empirically verify the effectiveness of the multilayer cross‐fusion with the reconstructor structure on the proposed model. [ABSTRACT FROM AUTHOR]

China's "two sessions," namely, the National People's Congress (NPC) and the Chinese People's Political Consultative Conference (CPPCC), has significant meaning to the political life of the nation. It collects opinions and advice from different groups of people annually. "Two sessions" 2013 was especially eye-catching, because new state leaders were elected at the meetings. Using CATI (Computer Assisted Telephone Interviewing) system, the Media and Public Opinion Center of Fudan University (FMORC) conducted surveys of China's "two sessions" every year from 2007 to 2013. In 2013, the influence of new media on public opinion has become increasingly significant. Microblog and WeChat have become two types of important media for Shanghai residents to express their opinions and take part in China's "two sessions." Based on the empirical findings, this paper examines Shanghai Residents' cognition, attitudes and expressions towards "two sessions" 2013 and analyzes how new media affect the public opinions on significant political events.