Search

The aim of the work is to prove the possibility of determining the representativeness of a corpus for training a neural model before conducting resource-intensive experiments. In this work, we investigated the dependence of the summarization model on the number of word stems in it. The work was carried out on a synthetic summarization dataset for the Kazakh language. Taking the number of word stems as the representativeness metric, an analysis of the quality of the work of three summarization models was performed depending on the number of word stems in the training dataset. These training datasets differ in the number of rows. To obtain these datasets, we split the training dataset into three parts of different sizes. On the test files, BLEU scores were obtained for each model during the inference process. The highest BLEU scores are obtained for the model trained on the largest amount of data. When the train dataset was reduced by 50 percent, the score decreased from 4 to 25. On the smallest dataset, the score dropped from 25 to 31. The experimental part of the work showed that the model with the largest number of stems shows the highest BLEU score. The scientific contribution of the work is the experimental proof of the representativeness of the training corpus by the number of stems before training the neural model. [ABSTRACT FROM AUTHOR]

Texts used in L2 classrooms have traditionally been simplified manually, but recent technological advances allow us to investigate whether automatic text simplification (ATS) software can help L2 learners comprehend texts in second and foreign languages. Participants were divided into low and high L2 reading proficiency groups and assigned to read either the authentic or automatically simplified version of a text and completed a free recall task and MC comprehension test. The results did not show any significant correlations among the variables of topic knowledge, topic interest, and MC comprehension, but there were correlations among L2 reading comprehension, MC comprehension, and free recall results. Results also showed that the automatically simplified text facilitated the comprehension of the more proficient readers but not the less proficient readers according to their performance on the free recall assessment. Implications are that L2 teachers cannot blindly use whatever text they want with ATS, and ATS software designers may need to reconsider the current conservative approach to simplification that many ATS tools use. [ABSTRACT FROM AUTHOR]

Nowadays, there is an abundance of information available from both online and offline sources. For a single topic, we can get more than hundreds of sources containing a wealth of information. The ability to extract or generate a summary of popular content allows users to quickly search for content and obtain preliminary data in the shortest amount of time. Manually extracting useful information from them is a difficult task. Automatic text summarization (ATS) systems are being developed to address this issue. Text summarization is the process of extracting useful information from large documents and compressing it into a summary while retaining all the relevant contents. This review paper provides a broad overview of ATS research works in various Ethiopian languages such as Amharic, Afan Oromo, and Tigrinya using different text summarization approaches. The work has identified the novel and recommended state-of-the-art techniques and methods for future researchers in the area and provides knowledge and useful support to new researchers in this field by providing a concise overview of the various feature extraction methods and classification techniques required for different types of ATS approaches applied to the Ethiopian languages. Finally, different recommendations for future researchers have been forwarded. [ABSTRACT FROM AUTHOR]

The traditional Encoder-Decoder model with attention mechanism has such problems as text redundancy, inconsistent representation and out of vocabulary (OOV) in the application of the summary task, resulting in low accuracy of the generated summary. The transformer model with ambeddable text location information was improved, pointer network was introduced to help with decoding, and take advantage of pointer network to generated text to generate summary. The effectiveness of the transformer model was verified on the LCSTS Chinese short text summary data set. The results show that the model outperforms the benchmark model by an average of two points in ROUGE scores, and the prominence of the generated content and the fluency of the language are significantly improved while ensuring the consistency of the summary with the input text. [ABSTRACT FROM AUTHOR]

Nowadays we see huge amount of information is available on both, online and offline sources. For single topic we see hundreds of articles are available, containing vast amount of information about it. It is really a difficult task to manually extract the useful information from them. To solve this problem, automatic text summarization systems are developed. Text summarization is a process of extracting useful information from large documents and compressing them into short summary preserving all important content. This survey paper hand out a broad overview on the work done in the field of automatic text summarization in different languages using various text summarization approaches. The focal centre of this survey paper is to present the research done on text summarization on Indian languages such as, Hindi, Punjabi, Bengali, Malayalam, Kannada, Tamil, Marathi, Assamese, Konkani, Nepali, Odia, Sanskrit, Sindhi, Telugu and Gujarati and foreign languages such as Arabic, Chinese, Greek, Persian, Turkish, Spanish, Czeh, Rome, Urdu, Indonesia Bhasha and many more. This paper provides the knowledge and useful support to the beginner scientists in this research area by giving a concise view on various feature extraction methods and classification techniques required for different types of text summarization approaches applied on both Indian and non-Indian languages. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Evaluation is crucial in the research and development of automatic summarization applications, in order to determine the appropriateness of a summary based on different criteria, such as the content it contains, and the way it is presented. To perform an adequate evaluation is of great relevance to ensure that automatic summaries can be useful for the context and/or application they are generated for. To this end, researchers must be aware of the evaluation metrics, approaches, and datasets that are available, in order to decide which of them would be the most suitable to use, or to be able to propose new ones, overcoming the possible limitations that existing methods may present. In this article, a critical and historical analysis of evaluation metrics, methods, and datasets for automatic summarization systems is presented, where the strengths and weaknesses of evaluation efforts are discussed and the major challenges to solve are identified. Therefore, a clear up-to-date overview of the evolution and progress of summarization evaluation is provided, giving the reader useful insights into the past, present and latest trends in the automatic evaluation of summaries. [ABSTRACT FROM AUTHOR]

The problem of factual incorrectness in machine-generated abstractive summarization has received widespread attention in the past few years. Although large-scale neural models show excellent capability in generating fluent and coherent summaries, they still struggle with factual inconsistency, in which the named entity incorrectness is the most frequent and notable one, especially for the character-based languages, such as Chinese. Since abstractive summaries are mostly generated character by character in Chinese, the problem of hallucinated entities is more severe than that of other word-based languages. In this paper, we propose CC-Gens, a novel approach for Correctness Checking based on a Generative negative sampling strategy. Considering that the problem is due to the uncertain nature of the language generation process, we leverage fine-tuned generative language models, i.e., UniLMv2 and mT5, to generate summaries with incorrect entities, thereby constructing a synthetic binary classification dataset for the factuality discriminative model. We propose three strategies: Entity Sampling, Sequence Sampling, and Cloze Sampling, to generate summaries with incorrect entities. With such strategies, the negative samples are much more similar in nature to the output of the neural summarization model. We then train a BERT-based discriminator to identify factually incorrect machine-generated summaries with entity errors based on these generative negative samples. We further propose a novel PU learning algorithm to improve the performance of our approach by iteratively training the discriminator to select high confident negative samples from the unlabeled model generated summaries to replace the former artificially constructed ones. By generating multiple candidate summaries and selecting the one with the highest factual correctness score among them, our approach can significantly reduce the probability that an output summary contains factual errors. According to a comprehensive evaluation, the CC-Gens we proposed outperforms previous works in identifying faithless summaries as well as providing faithful ones. [Display omitted] • Named entity error ratio in Chinese abstractive summaries is as high as 58.1%. • We propose generative negative sampling strategies for training the discriminator. • We apply PU learning to improve performance by selecting high-confident samples. [ABSTRACT FROM AUTHOR]

People affected by Autism Spectrum Disorders (ASD) have impairments in social interaction because they lack an adequate theory of mind. A significant percentile has inadequate reading comprehension skills. We present a multilingual tool called Open Book (OB) that applies Human Language Technologies (HLT) in order to identify reading comprehension obstacles in text documents and propose more simple alternatives with the aim of assisting the reading comprehension of users. OB involves several text transformations at lexical, syntactic and semantic level. In this paper we focus on three challenging components of the OB tool: the image retrieval component, the idiom detection component and the summarization module. There are very few studies that involve simplification by showing images associated to difficult concepts. In addition, the treatment of figurative language such as idioms or metaphors is one of the most challenging areas in Natural Language Processing (NLP). Finally, although text summarization is a more widely studied field in NLP, its application to text simplification remains as an open research issue. Thus, we focus on the integration of these three modules in our OB tool. We present the motivation for building these components and we describe how they are integrated in the whole system. Moreover, the usability and the usefulness of OB have been evaluated and analysed showing that the tool helps to produce texts easier to understand for autistic people. [ABSTRACT FROM AUTHOR]

Abstract: One of the main challenges to be addressed in text summarization concerns the detection of redundant information. This paper presents a detailed analysis of three methods for achieving such goal. The proposed methods rely on different levels of language analysis: lexical, syntactic and semantic. Moreover, they are also analyzed for detecting relevance in texts. The results show that semantic-based methods are able to detect up to 90% of redundancy, compared to only the 19% of lexical-based ones. This is also reflected in the quality of the generated summaries, obtaining better summaries when employing syntactic- or semantic-based approaches to remove redundancy. [Copyright &y& Elsevier]

Abstract: Concept map is a graphical tool for representing knowledge. They have been used in many different areas, including education, knowledge management, business and intelligence. Constructing of concept maps manually can be a complex task; an unskilled person may encounter difficulties in determining and positioning concepts relevant to the problem area. An application that recommends concept candidates and their position in a concept map can significantly help the user in that situation. This paper gives an overview of different approaches to automatic and semi-automatic creation of concept maps from textual and non-textual sources. The concept map mining process is defined, and one method suitable for the creation of concept maps from unstructured textual sources in highly inflected languages such as the Croatian language is described in detail. Proposed method uses statistical and data mining techniques enriched with linguistic tools. With minor adjustments, that method can also be used for concept map mining from textual sources in other morphologically rich languages. [Copyright &y& Elsevier]

This paper proposes a new method of enhancing the accuracy of a decomposition task by using position checking and a semantic measure for each word within a summary document. The proposed model is an extension of the Hidden Markov Model for the human-written decomposition problem. Experimental results using DUC data and the Telecommunication Corpus show that the proposed method improves the accuracy of decomposition of human-written summary sentences. [ABSTRACT FROM AUTHOR]