Search results

In the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.

To overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.

Summaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.

This paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.

This study examines the impact of different Balanced Scorecard (BSC) formats (table, graph without summary measure, graph with a summary measure) on various decision outcomes: performance ratings, perceived informativeness, and decision efficiency.

Using an original case developed by the researchers, a total of 135 individuals participated in the experiment and rated the performance of carwash managers in two different scenarios: one manager excelled financially but failed to meet targets for all other three BSC perspectives and the other manager had the opposite results.

The evaluators rated managerial performance significantly lower in the graph format compared to a table presentation of the BSC. Performance ratings were significantly higher for the scenario where the manager failed to meet only financial perspective targets but exceeded targets for all other nonfinancial BSC perspectives, contrary to the usual predictions based on the financial measure bias. The evaluators reported that informativeness of the BSC was highest in the table or graph without summary measure formats, and, surprisingly, adding a summary measure to the graph format significantly reduced perceived informativeness compared to the table format. Decision efficiency was better for the graph formats (with or without summary measure) than for the table format.

Ours is the first study to compare tables, graphs with and without a summary measure in the context of managerial performance evaluations and to examine their impact on ratings, informativeness, and efficiency. We developed an original case to test the boundaries of the financial measure bias.

Search engine users are faced with long lists of search results, each entry being of a varying degree of relevance. Often users' expectations based on the short text of a search result hold false expectations about the linked web page. This leads users to skip relevant information, missing valuable insights, and click on irrelevant web pages wasting time. The purpose of this paper is to propose a new summary generation technique, ReClose, which combines query‐independent and query‐biased summary techniques to improve the accuracy of users' expectations.

The authors tested the effectiveness of ReClose summaries against Google summaries by surveying 34 participants. Participants were randomly assigned to use one type of summary approach. Summary effectiveness was judged based on the accuracy of each user's expectations.

It was found that individuals using ReClose summaries showed a 10 per cent increase in the expectation accuracy over individuals using Google summaries, and therefore better user satisfaction.

The survey demonstrates the effectiveness of using ReClose summaries to improve the accuracy of user expectations.

This paper presents a novel summary generation technique called ReClose, a new approach to summary evaluation and improvements upon previously proposed summary generation techniques.

Query-based summarization approaches might not be able to provide summaries compatible with the user’s information need, as they mostly rely on a limited source of information, usually represented as a single query by the user. This issue becomes even more challenging when dealing with scientific documents, as they contain more specific subject-related terms, while the user may not be able to express his/her specific information need in a query with limited terms. This study aims to propose an interactive multi-document text summarization approach that generates an eligible summary that is more compatible with the user’s information need. This approach allows the user to interactively specify the composition of a multi-document summary.

This approach exploits the user’s opinion in two stages. The initial query is refined by user-selected keywords/keyphrases and complete sentences extracted from the set of retrieved documents. It is followed by a novel method for sentence expansion using the genetic algorithm, and ranking the final set of sentences using the maximal marginal relevance method. Basically, for implementation, the Web of Science data set in the artificial intelligence (AI) category is considered.

The proposed approach receives feedback from the user in terms of favorable keywords and sentences. The feedback eventually improves the summary as the end. To assess the performance of the proposed system, this paper has asked 45 users who were graduate students in the field of AI to fill out a questionnaire. The quality of the final summary has been also evaluated from the user’s perspective and information redundancy. It has been investigated that the proposed approach leads to higher degrees of user satisfaction compared to the ones with no or only one step of the interaction.

The interactive summarization approach goes beyond the initial user’s query, while it includes the user’s preferred keywords/keyphrases and sentences through a systematic interaction. With respect to these interactions, the system gives the user a more clear idea of the information he/she is looking for and consequently adjusting the final result to the ultimate information need. Such interaction allows the summarization system to achieve a comprehensive understanding of the user’s information needs while expanding context-based knowledge and guiding the user toward his/her information journey.

The paper's aim is to measure the effect of various brief summary formats on consumers' drug‐related knowledge, evaluations of ad information, ad believability, attitudes towards the ad and brand, perceived product risk and intention to use ad information in making healthcare decisions.

Using mall‐intercept surveys, 307 US women, age 18‐50 years, were randomly assigned to one of the six different versions of brief summary formats for a birth control medicine. The six brief summary formats included: no brief summary, traditional (continuous prose) brief summary, risk information window, bulleted list, nutrition facts panel, and question‐answer format. The participants completed a closed‐ended questionnaire after reviewing the print ad.

MANOVA indicated presence of a multivariate main effect. However, univariate ANOVAs, performed to evaluate the effect of individual formats, revealed that the eight outcome variables did not vary significantly across the six brief summary formats. Nevertheless, respondents exhibited more positive evaluation of the newer brief summary formats compared to the traditional brief summary format, albeit there was no statistically significant difference among the newer formats.

Consumers clearly prefer newer brief summary formats to the traditional brief summary format.

This research provides additional insights about risk communication in direct‐to‐consumer ads and may assist the FDA in the development of a standardized regulatory structure for the future. Providing brief summary in a clearer, understandable, and consumer‐friendly manner can help consumers in deciding whether the drug is appropriate for their condition.

The goal of this paper is to contribute to the development of both data localization and description techniques in P2P systems.

The approach consists of introducing a novel indexing technique that relies on linguistic data summarization into the context of P2P systems.

The cost model of the approach, as well as the simulation results have shown that the approach allows the efficient maintenance of data summaries, without incurring high traffic overhead. In addition, the cost of query routing is significantly reduced in the context of summaries.

The paper has considered a summary service defined on the APPA's architecture. Future works have to study the extension of this work in order to be generally applicable to any P2P data management system.

This paper has mainly studied the quantitative gain that could be obtained in query processing from exploiting data summaries. Future works aim to implement this technique on real data (not synthetic) in order to study the qualitative gain that can be obtained from approximately answering a query.

The novelty of the approach shown in the paper relies on the double exploitation of the summaries in P2P systems: data summaries allow for a semantic‐based query routing, and also for an approximate query answering, using their intentional descriptions.

During crises such as accidents or disasters, an enormous volume of information is generated on the Web. Both people and decision-makers often need to identify relevant and timely content that can help in understanding what happens and take right decisions, as soon it appears online. However, relevant content can be disseminated in document streams. The available information can also contain redundant content published by different sources. Therefore, the need of automatic construction of summaries that aggregate important, non-redundant and non-outdated pieces of information is becoming critical.

The aim of this paper is to present a new temporal summarization approach based on a popular topic model in the information retrieval field, the Latent Dirichlet Allocation. The approach consists of filtering documents over streams, extracting relevant parts of information and then using topic modeling to reveal their underlying aspects to extract the most relevant and novel pieces of information to be added to the summary.

The performance evaluation of the proposed temporal summarization approach based on Latent Dirichlet Allocation, performed on the TREC Temporal Summarization 2014 framework, clearly demonstrates its effectiveness to provide short and precise summaries of events.

Unlike most of the state of the art approaches, the proposed method determines the importance of the pieces of information to be added to the summaries solely relying on their representation in the topic space provided by Latent Dirichlet Allocation, without the use of any external source of evidence.

The purpose of this research is to develop a method for automatic construction of multi‐document summaries of sets of news articles that might be retrieved by a web search engine in response to a user query.

Based on the cross‐document discourse analysis, an event‐based framework is proposed for integrating and organizing information extracted from different news articles. It has a hierarchical structure in which the summarized information is presented at the top level and more detailed information given at the lower levels. A tree‐view interface was implemented for displaying a multi‐document summary based on the framework. A preliminary user evaluation was performed by comparing the framework‐based summaries against the sentence‐based summaries.

In a small evaluation, all the human subjects preferred the framework‐based summaries to the sentence‐based summaries. It indicates that the event‐based framework is an effective way to summarize a set of news articles reporting an event or a series of relevant events.

Limited to event‐based news articles only, not applicable to news critiques and other kinds of news articles. A summarization system based on the event‐based framework is being implemented.

Multi‐document summarization of news articles can adopt the proposed event‐based framework.

An event‐based framework for summarizing sets of news articles was developed and evaluated using a tree‐view interface for displaying such summaries.

The purpose of this paper is to discuss the SEC's Proposed Release 33‐8861 of November 21, 2007, “Enhanced disclosure and new prospectus delivery option for registered open‐end management investment companies.”

The paper provides an overview of the proposed rule. It then discusses its impact on the industry, investors, and the environment; and how the summary prospectus could impact retirement plans. The paper answers some frequently asked questions; and provides an implementation timeline.

The paper finds that the SEC has proposed a rule for a shorter, simpler, standardized prospectus that would tell investors what they need to know within three to four pages and provide web access to more detailed information if desired. The stated goal is provide the average investor with clear, succinct information and also to standardize information to facilitate fund‐to‐fund comparisons. The summary prospectus also offers a significant opportunity to reduce publishing and mailing costs and may provide the mutual fund industry with the impetus to migrate from paper‐based to electronic disclosure.

The paper provides insight from a financial disclosure systems provider.

To analyze the SEC’s newly adopted Rule 498 A, the variable contract summary prospectus rule, and concurrently adopted prospectus disclosure requirements in order to propose to insurance companies issuing variable contracts a project implementation plan for companies seeking SEC approval for summary prospectuses compliant with the new rules.

Discusses the history, requirements, effects, and expected implementation timeline of the new rules, then offers a detailed project plan and timeline for compliance.

The Rule does not require insurers to use summary prospectuses, but there are several compelling reasons for doing so. The Rule allows insurers to use a new concise and brief selling document, and by so doing to begin generating very significant cost savings as soon as May 1, 2021. The article provides a detailed implementation plan for insurance companies that want to comply with the new prospectus disclosure requirements and implement policies and procedures to begin using summary prospectuses.

A coordinated project implementation plan like that outlined in the article might assist insurance companies to make the requisite statutory prospectus revisions and prepare and obtain SEC approval of summary prospectuses by May 1, 2021.

Analysis from experienced attorneys who frequently advise insurance companies issuing fixed and variable annuities, and assist clients in navigating the complex regulatory requirements governing insurance and securities products.