Narzędzia do automatycznego streszczania tekstów w języku polskim. Stan badań naukowych i prac wdrożeniowych

The goal of the publication is to present the state of research and works carried out in Poland on the issue of automatic text summarization. The author describes principal theoretical and methodological issues related to automatic summary generation followed by the outline of the selected works on the automatic abstracting of Polish texts. The author also provides three examples of IT tools that generate summaries of texts in Polish (Summarize, Resoomer, and NICOLAS) and their characteristics derived from the conducted experiment, which included quality assessment of generated summaries using ROUGE-N metrics. The results of both actions showed a deficiency of tools allowing to automatically create summaries of Polish texts, especially in the abstractive approach. Most of the proposed solutions are based on the extractive method, which uses parts of the original text to create its abstract. There is also a shortage of tools generating one common summary of many text documents and specialized tools generating summaries of documents related to specific subject areas. Moreover, it is necessary to intensify works on creating the corpora of Polish-language text summaries, which the computer scientists could apply to evaluate their newly developed tools.

Narzędzia do automatycznego streszczania tekstów w języku polskim. Stan badań naukowych i prac wdrożeniowych

The goal of the publication is to present the state of research and works carried out in Poland on the issue of automatic text summarization. The author describes principal theoretical and methodological issues related to automatic summary generation followed by the outline of the selected works on the automatic abstracting of Polish texts. The author also provides three examples of IT tools that generate summaries of texts in Polish (Summarize, Resoomer, and NICOLAS) and their characteristics derived from the conducted experiment, which included quality assessment of generated summaries using ROUGE-N metrics. The results of both actions showed a deficiency of tools allowing to automatically create summaries of Polish texts, especially in the abstractive approach. Most of the proposed solutions are based on the extractive method, which uses parts of the original text to create its abstract. There is also a shortage of tools generating one common summary of many text documents and specialized tools generating summaries of documents related to specific subject areas. Moreover, it is necessary to intensify works on creating the corpora of Polish-language text summaries, which the computer scientists could apply to evaluate their newly developed tools.

On the composition of scientific abstracts

Purpose – Scientific abstracts reproduce only part of the information and the complexity of argumentation in a scientific article. The purpose of this paper provides a first analysis of the similarity between the text of scientific abstracts and the body of articles, using sentences as the basic textual unit. It contributes to the understanding of the structure of abstracts. Design/methodology/approach – Using sentence-based similarity metrics, the authors quantify the phenomenon of text re-use in abstracts and examine the positions of the sentences that are similar to sentences in abstracts in the introduction, methods, results and discussion structure, using a corpus of over 85,000 research articles published in the seven Public Library of Science journals. Findings – The authors provide evidence that 84 percent of abstract have at least one sentence in common with the body of the paper. Studying the distributions of sentences in the body of the articles that are re-used in abstracts, the authors show that there exists a strong relation between the rhetorical structure of articles and the zones that authors re-use when writing abstracts, with sentences mainly coming from the beginning of the introduction and the end of the conclusion. Originality/value – Scientific abstracts contain what is considered by the author(s) as information that best describe documents’ content. This is a first study that examines the relation between the contents of abstracts and the rhetorical structure of scientific articles. The work might provide new insight for improving automatic abstracting tools as well as information retrieval approaches, in which text organization and structure are important features.

Research of Extracting Chinese Automatic Abstracting Processing Based on Semidiscrete Matrix Decomposition

This paper introduced six popular methods of automatic abstract.Finally，on the basis of LSI this paper proposed an approach of extracting sentences based on SDD sentences clustering

Research of Text Topic Automatic Extraction Method Based on Rough Set Theory

On the base of researching currently popular text topic extraction technologies, a new text topic automatic abstracting method is proposed based on rough set theory and rough similarity. Firstly it separated a text into words and sentences to complete information segmentation, and then constructed a similarity matrix by computing the rough similarity between different words to realize the text clustering, finally extracted representative sentences from each class to generate the text topic. The experiment shows that the method is feasible and effective.