Search

This paper proposes a counseling agent by ELIZA-like but much more human-centered (we call "context? respectful") dialogue, respecting human namely clients' suffering situation/ context. Towards self-awareness of solutions through reflection, this reflection agent can perform context-respectful support. Building up mutual trust or empathizing with the client and keeping it, this agent supports clients to identify and clarify/ dig their problem using problem-clarification words and summarizing several client's events and emotions. The summarization condenses the essence and/or detects the inconsistencies of what clients said, which encourage clients reflect themselves to their problem clarification. In other words, the summarization is considered as paraphrasing in not only a single dialog step (ELIZA-like mirroring in some means) but also several steps of a dialog. This context-respectful text summarization, keeping the counseling conversation continuing, promotes the clients' deeper clarification of the problem through self-reflection towards clients' self-awareness of solutions. Further, utilizing the context /situation based software decomposition as well as limiting the problem domain makes the counseling software agent easily realized with-out acquiring and managing a tremendous amount of knowledge. The pre-evaluation shows the promising result of the method. [ABSTRACT FROM PUBLISHER]

In mobile devices, limited space and time for browsing contents of web pages is an important issue. Summarization solutions running on web browsers can help the user to view and access summarized content of web pages in real time. In this paper we propose a framework for summarizing text viewed through mobile web browsers. The framework consists of an application that runs as part the mobile browser and extracts raw text. The text is then preprocessed and input to the summarization algorithm. The algorithm can be implemented either on the device as part of the browser engine or on a remote cloud service. The cloud service uses appropriate techniques to summarize the text and returns the summarized content to the device, where it is then displayed. During summarization, an extraction algorithm is used that uses ontology and a weighing mechanism to determine suitability score for each sentence. The sentences with the highest suitability scores are selected for inclusion in the summary as per the compression required. We describe a number of user interface elements in the mobile web browser to trigger the summarization and display the results, and compare the performance of publicly available summarization services. [ABSTRACT FROM PUBLISHER]

Text Summarization is condensing the source text into a shorter version preserving its information content and overall meaning. It is very difficult for human beings to manually summarize large documents of text. The text summarization method consists of selecting important sentences, paragraphs etc. from the original document and converting them into a star map. The importance of sentences is decided based on statistical and linguistic features of sentences. A star map summarization method consists of understanding the original text and re-telling it in fewer words. This star map is used for duplicate elimination, exam paper evaluator, lesson planning, Identify Shingling. A Pioneering Tool For Text Summarization using Star Map has been presented. [ABSTRACT FROM PUBLISHER]

During software evolution a developer must investigate source code to locate then understand the entities that must be modified to complete a change task. To help developers in this task, Haiduc et al. proposed text summarization based approaches to the automatic generation of class and method summaries, and via a study of four developers, they evaluated source code summaries generated using their techniques. In this paper we propose a new topic modeling based approach to source code summarization, and via a study of 14 developers, we evaluate source code summaries generated using the proposed technique. Our study partially replicates the original study by Haiduc et al. in that it uses the objects, the instruments, and a subset of the summaries from the original study, but it also expands the original study in that it includes more subjects and new summaries. The results of our study both support the findings of the original and provide new insights into the processes and criteria that developers use to evaluate source code summaries. Based on our results, we suggest future directions for research on source code summarization. [ABSTRACT FROM PUBLISHER]

The work focuses on the integration of text categorization and text summarization tasks based on some existing algorithms. We primarily employ the method for bioinformatics literatures to categorize them in relevant domains of bioinformatics and then get a summarized overview of each of the documents in the domain. For text categorization we have chosen three different and core domains of bioinformatics: Protein-Protein Interaction, Disease-Drug Relevance and Pathway-Process Involvement. The method uses TF-IDF based technology for the categorization task and then after categorization it summarizes the key contents of each document using some existing features. The system plays important role in automatically reducing review spaces for the researchers as they do not need to manually select their relevant texts. It also saves time by providing ranked and significantly relevant lines of the documents. Our method outperforms other existing summarization tools in the sense that it optimizes summarization by first categorizing the documents on the basis of TF-IDF technology and then avoids redundant information by properly ranking the sentences using existing score. [ABSTRACT FROM PUBLISHER]

This paper presents a mining tool that is able to extract graphs from texts, and proposes their use in helping students to write summaries. The text summarization method is based on the use of the graphs as graphic organizers, leading students to further reflect about the main ideas of the text before getting to the actual task of writing. An experiment carried out demonstrated that the tool helped students reflect about the main ideas of the text and supported the writing of the summaries. [ABSTRACT FROM PUBLISHER]

Millions of text contents and multimedia published on the Web have potential to be shared as the learning contents. However, mobile learners often feel it difficult to extract useful contents for learning. Manually creating content not only requires a huge effort on the part of the teachers but also creates barriers towards reuse of the content that has already been created for e-Learning. In this paper, a text-based content summarizer is introduced to address an approach to help mobile learners to retrieve and process information more quickly by aligning text-based content size to various mobile characteristics. In this work, probabilistic language modeling techniques are integrated into an extractive text summarization system to fulfill the automatic summary generation for mobile learning. Experimental results have shown that our solution is a proper and efficient approach to help mobile learners to summarize important content quickly. [ABSTRACT FROM PUBLISHER]