summarization is a challenging task that aims to generate a summary by grasping common information of a given set of information. Text summarization is a popular task of determining the topic or generating a textual s...
详细信息
summarization is a challenging task that aims to generate a summary by grasping common information of a given set of information. Text summarization is a popular task of determining the topic or generating a textual summary of documents. In contrast, image summarization aims to find a representative summary of a collection of images. However, current methods are still restricted to generating a visual scene graph, tags, and noun phrases, but cannot generate a fitting textual description of an image collection. Thus, we introduce a novel framework for generating a summarized caption of an image collection. Since scene graph generation shows advancement in describing objects and their relationships on a single image, we use it in the proposed method to generate a scene graph for each image in an image collection. Then, we find common objects and their relationships from all scene graphs and represent them as a summarized scene graph. For this, we merge all scene graphs and select part of it by estimating the most common objects and relationships. Finally, the summarized scene graph is input into a captioning model. In addition, we introduce a technique to generalize specific words in the final caption into common concept words incorporating external knowledge. To evaluate the proposed method, we construct a dataset for this task by extending the annotation of the MS-COCO dataset using an image retrieval method. The evaluation of the proposed method on this dataset showed promising performance compared to text summarization-based methods.
The headline of a news article is designed to succinctly summarize its content, providing the reader with a clear understanding of the news item. Unfortunately, in the post-truth era, headlines are more focused on att...
详细信息
The headline of a news article is designed to succinctly summarize its content, providing the reader with a clear understanding of the news item. Unfortunately, in the post-truth era, headlines are more focused on attracting the reader's attention for ideological or commercial reasons, thus leading to mis- or disinformation through false or distorted headlines. One way of combating this, although a challenging task, is by determining the relation between the headline and the body text to establish the stance. Hence, to contribute to the detection of mis- and disinformation, this paper proposes an approach (HeadlineStanceChecker) that determines the stance of a headline with respect to the body text to which it is associated. The novelty rests on the use of a two-stage classification architecture that uses summarization techniques to shape the input for both classifiers instead of directly passing the full news body text, thereby reducing the amount of information to be processed while keeping important information. Specifically, summarization is done through Positional Language Models leveraging on semantic resources to identify salient information in the body text that is then compared to its corresponding headline. The results obtained show that our approach achieves 94.31% accuracy for the overall classification and the best FNC-1 relative score compared with the state of the art. It is especially remarkable that the system, which uses only the relevant information provided by the automatic summaries instead of the whole text, is able to classify the different stance categories with very competitive results, especially in the discuss stance between the headline and the news body text. It can be concluded that using automatic extractive summaries as input of our approach together with the two-stage architecture is an appropriate solution to the problem. (C) 2021 The Author(s). Published by Elsevier B.V.
Automatic text summarization essentially condenses a long document into a shorter format while preserving its information content and overall meaning. It is a potential solution to the information overload. Several au...
详细信息
Automatic text summarization essentially condenses a long document into a shorter format while preserving its information content and overall meaning. It is a potential solution to the information overload. Several automatic summarizers exist in the literature capable of producing high-quality summaries, but they do not focus on preserving the underlying meaning and semantics of the text. In this paper, we capture and preserve the semantics of text as the fundamental feature for summarizing a document. We propose an automatic summarizer using the distributional semantic model to capture semantics for producing high-quality summaries. We evaluated our summarizer using ROUGE on DUC-2007 dataset and compare our results with other four different state-of-the-art summarizers. Our system outperforms the other reference summarizers leading us to the conclusion that usage of semantic as a feature for text summarization provides improved results and helps to further reduce redundancies from the input source. (C) 2019 Published by Elsevier Ltd.
Documents' summarization techniques automatically extract relevant information from different sources with respect to a list of topics: they can be profitably used by a variety of applications and in particular fo...
详细信息
ISBN:
(纸本)9780769541549
Documents' summarization techniques automatically extract relevant information from different sources with respect to a list of topics: they can be profitably used by a variety of applications and in particular for automatic indexing and categorization in order to facilitate the production and delivery of new multimedia contents. In this paper we propose a novel approach for summarizing documents retrieved from the Internet: we propose to capture the semantic nature of a document, expressed in natural language, in order to retrieve a number of RDF triplets and to clusterize these ones aggregating similar information. An overview of the system and some preliminary results are described.
In this paper, we analyze Community QuestionAnswer(CQA) contents from intent viewpoint of the query. Our statistical analysis results show that CQA information matched with keywords in the query is useful to find poss...
详细信息
In this paper, we analyze Community QuestionAnswer(CQA) contents from intent viewpoint of the query. Our statistical analysis results show that CQA information matched with keywords in the query is useful to find possible intents behind the query. Especially we find that a QA pair in CQA is possible semantic summarization of intent, following the assumption that the question is a useful expression of questioner's intent.
A personalized video summary is dynamically generated in our video personalization and summarization system based on user preference and usage environment. The three-tier personalization system adopts the server-middl...
详细信息
ISBN:
(纸本)0819451258
A personalized video summary is dynamically generated in our video personalization and summarization system based on user preference and usage environment. The three-tier personalization system adopts the server-middle ware-client architecture in order to maintain, select, adapt, and deliver rich media content to the user. The server stores the content sources along with their corresponding MPEG-7 metadata descriptions. In this paper, the metadata includes visual semantic annotations and automatic speech transcriptions. Our personalization and summarization engine in the middleware selects the optimal set of desired video segments by matching shot annotations and sentence transcripts with user preferences. Besides finding the desired contents, the objective is to present a coherent summary. There are diverse methods for creating summaries, and we focus on the challenges of generating a hierarchical video summary based on context information. In our summarization algorithm, three inputs are used to generate the hierarchical video summary output. These inputs are (1) MPEG-7 metadata descriptions of the contents in the server, (2) user preference and usage environment declarations from the user client, and (3) context information including MPEG-7 controlled term list and classification scheme. In a video sequence, descriptions and relevance scores are assigned to each shot. Based on these shot descriptions, context clustering is performed to collect consecutively similar shots to correspond to hierarchical scene representations. The context clustering is based on the available context information, and may be derived from domain knowledge or rules engines. Finally, the selection of structured video segments to generate the hierarchical summary efficiently balances between scene representation and shot selection.
暂无评论