Chinese Text Summarization Research Articles

An Improved mT5 Model for Chinese Text Summary Generation

Complicated policy texts require a lot of effort to read, so there is a need for intelligent interpretation of Chinese policies. To better solve the Chinese Text Summarization task, this paper utilized the mT5 model as the core framework and initial weights. Additionally, In addition, this paper reduced the model size through parameter clipping, used the Gap Sentence Generation (GSG) method as unsupervised method, and improved the Chinese tokenizer. After training on a meticulously processed 30GB Chinese training corpus, the paper developed the enhanced mT5-GSG model. Then, when fine-tuning the Chinese Policy text, this paper chose the idea of “Dropout Twice”, and innovatively combined the probability distribution of the two Dropouts through the Wasserstein distance. Experimental results indicate that the proposed model achieved Rouge-1, Rouge-2, and Rouge-L scores of 56.13%, 45.76%, and 56.41% respectively on the Chinese policy text summarization dataset.

Chinese Text Summarization Generation Algorithm based on ERNIE-GEN with Few-shot Learning

In view of the problems of exposure bias and insufficient annotation data in the existing Chinese short text summary algorithms, a new pre-training short text summary algorithm named ERNIE-GEN-CTS based on ERNIE-GEN is proposed. This paper uses pre-training language model to realize the double attention of word level and word level for short text, and fills the sub block with semantic information to optimize the exposure bias problem. After the pre-training model of large-scale Chinese corpus, the results are improved in LCSTS data set after the task tuning of the downstream summary, and the validity and stability of the model are verified.

Global Encoding for Long Chinese Text Summarization

Text summarization is one of the significant tasks of natural language processing, which automatically converts text into a summary. Some summarization systems, for short/long English, and short Chinese text, benefit from advances in the neural encoder-decoder model because of the availability of large datasets. However, the long Chinese text summarization research has been limited to datasets of a couple of hundred instances. This article aims to explore the long Chinese text summarization task. To begin with, we construct a first large-scale, long Chinese text summarization corpus, the Long Chinese Summarization of Police Inquiry Record Text (LCSPIRT). Based on this corpus, we propose a sequence-to-sequence (Seq2Seq) model that incorporates a global encoding process with an attention mechanism. Our model achieves a competitive result on the LCSPIRT corpus compared with several benchmark methods.

Chinese long text summarization using improved sequence-to-sequence lstm

Text summarization is an important issue in natural language processing. The existing method has the problem of low accuracy when performing long text summarization. In this paper, We use the LSTM to construct the sequence-to-sequence model, and combine the attention mechanism to process automatic Chinese long text summarization.The experimental results indicate that our method can accurately extract key information from long text, generate high-quality summary.

A Two-stage Chinese text summarization algorithm using keyword information and adversarial learning

At present, most Chinese text summarization algorithms use the sequence-to-sequence model, but this model is prone to the problems of unknown words and incomplete content generation. To address these problems, we propose a new two-stage automatic text summarization method using keyword information and adversarial learning in this paper. On the one hand, the proposed method integrates the keyword information into the sequence-to-sequence model. The main information and keywords of the article are considered simultaneously through the attention mechanism to improve the information of summary generation. On the other hand, adversarial learning is introduced into the proposed model to avoid the problem that the semantic vector after passing through the encoder cannot save the context information better. Experiments are carried out on the Chinese dataset LCSTS, and the comparison results show that the proposed method has advantages in abstractive summarization.

Selective and Coverage Multi-head Attention for Abstractive Summarization

Although the Transformer model has outperformed traditional sequence-to-sequence model in a variety of natural language processing (NLP) tasks, it still suffers from semantic irrelevance and repetition for abstractive text summarization. The main reason is that the long text to be summarized is usually composed of multi-sentences and has much redundant information. To tackle this problem, we propose a selective and coverage multi-head attention framework based on the original Transformer. It contains a Convolutional Neural Network (CNN) selective gate, which combines n-gram features with whole semantic representation to obtain core information from the long input sentence. Besides, we use a coverage mechanism in the multi-head attention to keep track of the words which have been summarized. The evaluations on Chinese and English text summarization datasets both demonstrate that the proposed selective and coverage multi-head attention model outperforms the baseline models by 4.6 and 0.3 ROUGE-2 points respectively. And the analysis shows that the proposed model generates the summary with higher quality and less repetition.

Chinese Text Summarization Algorithm Based on Word2vec

In order to extract some sentences that can cover the topic of a Chinese article, a Chinese text summarization algorithm based on Word2vec is used in this paper. Words in an article are represented as vectors trained by Word2vec, the weight of each word, the sentence vector and the weight of each sentence are calculated by combining word-sentence relationship with graph-based ranking model. Finally the summary is generated on the basis of the final sentence vector and the final weight of the sentence. The experimental results on real datasets show that the proposed algorithm has a better summarization quality compared with TF-IDF and TextRank.

Automatic Extraction of Key Sentences via Word Sense Identification for Chinese Text Summarization

In this paper, a novel method of key sentences extraction is proposed for automatic Chinese text summarization. Key-senses/sense-patterns discovery and key sentences extraction are its two main components. Since there is no Chinese lexical database like WordNet available to the authors, a compromise is to word-segment, POS-tag a target Chinese text and translate all the nouns/verbs into English for sense disambiguation using WordNet. The characteristic of the proposed method is that each sentence is represented by senses and the key senses in each sentence form a fuzzy transaction. Each entry of the fuzzy transaction is the maximum similarity degree of the corresponding key sense with each of the senses in the sentence. A prototype of this automatic Chinese text summarization scheme is constructed and an intrinsic method with the information-retrieval criteria is used for measuring the summary quality. The results of applying the prototype to datasets with manually-generated summaries are shown.

Selected Papers from TAAI2005

The annual Conference on Artificial Intelligence and Applications (TAAI), held in Taiwan and hosted by the Taiwanese Association of Artificial Intelligence and other academic institution, has expanded to an international forum following the success of its previous nine conferences. It hopes to bring together researchers and scholars in all areas of artificial intelligence from leading institutes and industries worldwide to exchange ideas on these hi-tech fields. Over 200 papers and 6 special issues consisting of 30 invited papers were presented, making TAAI 2005 the greatest in the TAAI series. This special issue presents 11 papers from this prestigious event, each of which has received outstanding recommendations from the reviewers and has been revised by authors for this publication. These papers detail a variety of applications of different artificial intelligent technologies, ranging from nonlinear programming, data classification, dynamic knowledge acquisition, and complex time-series prediction to liver disease classification and automatic Chinese text summarization. Some also deal with theoretical aspect of intelligent technologies, including genetic algorithms, neural networks, support vector machines, ant-colony algorithms, and pseudo-Boolean functions. This issue thus concisely summarizes recent advances in artificial intelligence and its applications. We are sure that you will find it a valuable resource in the AI research community, and hope that it will inspire our readers in the development of new applications and advanced intelligent systems. As guest editors of this special issue, we would like to express our sincere gratitude to all of the authors for contributing their work to this special issue and to thank the referees for their untiring efforts to complete reviews within a limited time. Thanks also go to Mr. Kazuki Ohmori of Fuji Technology Press for his kind assistance in the publication of this special issue. Last but not least, we thank JACIII Editor-in-Chief Kaoru Hirota for the enthusiastic hospitality with which JACIII has supported this special issue.

Using LSA and text segmentation to improve automatic Chinese dialogue text summarization

Automatic Chinese text summarization for dialogue style is a relatively new research area. In this paper, Latent Semantic Analysis (LSA) is first used to extract semantic knowledge from a given document, all question paragraphs are identified, an automatic text segmentation approach analogous to TextTiling is exploited to improve the precision of correlating question paragraphs and answer paragraphs, and finally some “important” sentences are extracted from the generic content and the question-answer pairs to generate a complete summary. Experimental results showed that our approach is highly efficient and improves significantly the coherence of the summary while not compromising informativeness.