Maximal Marginal Relevance Research Articles

An effective framework for measuring the novelty of scientific articles through integrated topic modeling and cloud model

Novelty is a critical characteristic of innovative scientific articles, and accurately identifying novelty can facilitate the early detection of scientific breakthroughs. However, existing methods for measuring novelty have two main limitations: (1) Metadata-based approaches, such as citation analysis, are retrospective and do not alleviate the pressures of the peer review process or enable timely tracking of scientific progress; (2) Content-based methods have not adequately addressed the inherent uncertainty between the qualitative concept of novelty and the textual representation of papers. To address these issues, we propose a practical and effective framework for measuring the novelty of scientific articles through integrated topic modeling and cloud model, referred to as MNSA-ITMCM. In this framework, papers are represented as topic combinations, and novelty is reflected in the organic reorganization of these topics. We use the BERTopic model to generate semantically informed topics, and then apply a topic selection algorithm based on maximum marginal relevance to obtain a topic combination that balances similarity and diversity. Furthermore, we leverage the cloud model from fuzzy mathematics to quantify novelty, overcoming the uncertainty inherent in natural language expression and topic modeling to improve the accuracy of novelty measurement. To validate the effectiveness of our framework, we conducted empirical evaluations on papers from the Cell 2021 journal (biomedical domain) and the ICLR 2023 conference (computer science domain). Through correlation analysis and prediction error analysis, our framework demonstrated the ability to identify different types of novel papers and accurately predict their novelty levels. The proposed framework is applicable across diverse scientific disciplines and publication venues, benefiting researchers, librarians, science evaluation agencies, policymakers, and funding organizations by improving the efficiency and comprehensiveness of identifying novelty research.

Extracting Key-phrase Embedding using Deep Average Network and Maximal Marginal Relevance to Enhance Information Retrieval

Background: Automatic keyphrase extraction (AKE) is essential to many NLP and information retrieval tasks. Extracting high-quality key phrases is difficult due to technological advancements and the exponential growth ‎of ‎textual data and digital sources. Unsupervised keyphrase extraction with cheap computing cost that relies ‎on ‎heuristic notions of phrase importance such as embedding similarities but their development necessitates in-depth subject expertise. Materials and Methods: This paper presents a method to obtain a semantic understanding of the query ‎and index documents by using ‎the embedding technique(universal Sentence ‎encoder (USE) ) while keeping the most informative ‎using Maximal Marginal Relevance (MMR) and then scoring(an ‎inverted index) the most documents relevant to the query ‎vector to improve the ‎performance of IR systems.‎ Results: The proposed retrieval model implement on the (Fire2011) dataset. The final ‎stage was evaluating the results of the baseline and the results (indexing and ranking) by using mean average precision (MAP). The ‎result of the baseline was 0.61, while the result ‎inverted index was 0.6277519 .‎ Conclusions: In this paper, we have discussed document retrieval using keep key phrases that ‎have ‏informativeness ‎properties by ‎using maximal ‎marginal ‎relevance, since if we extract a fixed number of top ‎keyphrases, ‎redundancy ‎hinders the diversification of the ‎extracted keyphrases.

Exploring climate change discourse on social media and blogs using a topic modeling analysis

Climate change is one of the most pressing global issues of our time, and understanding public perception and awareness of the topic is crucial for developing effective policies to mitigate its effects. While traditional survey methods have been used to gauge public opinion, advances in natural language processing (NLP) and data visualization techniques offer new opportunities to analyze user-generated content from social media and blog posts. In this study, a new dataset of climate change-related texts was collected from social media sources and various blogs. The dataset was analyzed using BERTopic and LDA to identify and visualize the most important topics related to climate change. The study also used sentence similarity to determine the similarities in the comments written and which topic categories they belonged to. The performance of different techniques for keyword extraction and text representation, including OpenAI, Maximal Marginal Relevance (MMR), and KeyBERT, was compared for topic modeling with BERTopic. It was seen that the best coherence score and topic diversity metric were obtained with OpenAI-based BERTopic. The results provide insights into the public's attitudes and perceptions towards climate change, which can inform policy development and contribute to efforts to reduce activities that cause climate change.

Extractive social media text summarization based on MFMMR-BertSum

The advancement of computer technology has led to an overwhelming amount of textual information, hindering the efficiency of knowledge intake. To address this issue, various text summarization techniques have been developed, including statistics, graph sorting, machine learning, and deep learning. However, the rich semantic features of text often interfere with the abstract effects and lack effective processing of redundant information. In this paper, we propose the Multi-Features Maximal Marginal Relevance BERT (MFMMR-BertSum) model for Extractive Summarization, which utilizes the pre-trained model BERT to tackle the text summarization task. The model incorporates a classification layer for extractive summarization. Additionally, the Maximal Marginal Relevance (MMR) component is utilized to remove information redundancy and optimize the summary results. The proposed method outperforms other sentence-level extractive summarization baseline methods on the CNN/DailyMail dataset, thus verifying its effectiveness.

Extractive Summarization of Telugu Text Using Modified Text Rank and Maximum Marginal Relevance

With the rapid growth of digital content, there is a need for an automatic text summarizer to provide short text from a long text document. Many research works have been presented for extractive text summarization (ETS). This article mainly focuses on the graph-based ETS approach for multiple Telugu text documents. A modified Text-Rank algorithm is employed with the noun and verb count of each sentence in the text as the initial score of each node. To get the optimal features, a novel feature selection algorithm called improved Flamingo Search Algorithm is proposed in this article. Though graph-based ETS is an important approach, the generated summaries are redundant. To reduce the redundancy in the generated summary, maximum marginal relevance is combined with the modified Text-Rank. Different word-embedding techniques such as Fast-Text, Word2vec, TF-IDF, and one-hot encoding are utilized to experiment with the proposed approach. The performance of the proposed text summarization approach is evaluated with BLEU and ROUGE in terms of F-measure, precision, and recall.

Maximum Marginal Relevance and Vector Space Model for Summarizing Students' Final Project Abstracts

Automatic summarization is reducing a text document with a computer program to create a summary that retains the essential parts of the original document. Automatic summarization is necessary to deal with information overload, and the amount of data is increasing. A summary is needed to get the contents of the article briefly. A summary is an effective way to present extended information in a concise form of the main contents of an article, and the aim is to tell the reader the essence of a central idea. The simple concept of a summary is to take an essential part of the entire contents of the article. Which then presents it back in summary form. The steps in this research will start with the user selecting or searching for text documents that will be summarized with keywords in the abstract as a query. The proposed approach performs text preprocessing for documents: sentence breaking, case folding, word tokenizing, filtering, and stemming. The results of the preprocessed text are weighted by term frequency-inverse document frequency (tf-idf), then weighted for query relevance using the vector space model and sentence similarity using cosine similarity. The next stage is maximum marginal relevance for sentence extraction. The proposed approach provides comprehensive summarization compared with another approach. The test results are compared with manual summaries, which produce an average precision of 88%, recall of 61%, and f-measure of 70%.

Applicability Analysis and Ensemble Application of BERT with TF-IDF, TextRank, MMR, and LDA for Topic Classification Based on Flood-Related VGI

Volunteered geographic information (VGI) plays an increasingly crucial role in flash floods. However, topic classification and spatiotemporal analysis are complicated by the various expressions and lengths of social media textual data. This paper conducted applicability analysis on bidirectional encoder representation from transformers (BERT) and four traditional methods, TextRank, term frequency–inverse document frequency (TF-IDF), maximal marginal relevance (MMR), and linear discriminant analysis (LDA), and the results show that for user type, BERT performs best on the Government Affairs Microblog, whereas LDA-BERT performs best on the We Media Microblog. As for text length, TF-IDF-BERT works better for texts with a length of <70 and length >140 words, and LDA-BERT performs best with a text length of 70–140 words. For the spatiotemporal evolution pattern, the study suggests that in a Henan rainstorm, the textual topics follow the general pattern of “situation-tips-rescue”. Moreover, this paper detected the hotspot of “Metro Line 5” related to a Henan rainstorm and discovered that the topical focus of the Henan rainstorm spatially shifts from Zhengzhou, first to Xinxiang, and then to Hebi, showing a remarkable tendency from south to north, which was the same as the report issued by the authorities. We integrated multi-methods to improve the overall topic classification accuracy of Sina microblogs, facilitating the spatiotemporal analysis of flooding.

Optimizing Multidocument Summarization by Blending Reinforcement Learning Policies

We consider extractive summarization within a cluster of related texts (multi-document summarization). Unlike single-document summarization, redundancy is particularly important because sentences across related documents might convey overlapping information. Thus, sentence extraction in such a setting is difficult because one will need to determine which pieces of information are relevant while avoiding unnecessary repetitiveness. To solve this difficult problem, we propose a novel reinforcement learning based method <inline-formula><tex-math notation="LaTeX">$\mathbf{PoBRL}$</tex-math></inline-formula> (<b>Po</b>licy <b>B</b>lending with maximal marginal relevance and <b>R</b>einforcement <b>L</b>earning) for solving multi-document summarization. PoBRL jointly optimizes over the following objectives necessary for a high-quality summary: importance, relevance, and length. Our strategy decouples this multi-objective optimization into different sub-problems that can be solved individually by reinforcement learning. Utilizing PoBRL, we then blend each learned policies to produce a summary that is a concise and a complete representation of the original input. Our empirical analysis shows high performance on several multi-document datasets. Human evaluation also shows that our method produces high-quality output.

Comment-enriched index terms improve the relevance and novelty of the ranking of the commented medical articles retrieved by an NLP system

PurposeThis study aimed to investigate how the enrichment of medical documents' index terms by their comments improves the relevance and novelty of the top-ranked results retrieved by an NLP system.Design/methodology/approachA semi-experimental pre-test and post-test research was designed to compare NLP-based indexes before and after being expanded by the comment terms. The experiments were conducted on a test collection of 13,957 documents commented by F1000-Prime reviewers. They were indexed at title, abstract, body and full-text levels. In total, 100 seed documents were randomly selected and served as queries. The textual similarity of the documents and queries was calculated using Lucene-more-like-this function and evaluated by the semantic similarity of their MeSH. The results novelty was measured using maximal marginal relevance and evaluated by their MeSH novelties. Normalized discounted cumulative gain was used to compare the basic and expanded indexes' precisions at 10, 20 and 50 top ranks.FindingsThe relevance and novelty of the results ranked at the top precision points was improved after expanding the indexes by the comment terms. The finding implies that meta-texts are effective in representing their mother documents, by adding dynamic elements to their rather static contents. It also provides further evidence about the merits of the application of social intelligence and collective wisdom reflected in the actions and reactions of users in tackling the challenges faced by NLP-based systems.Originality/valueThis is the first study to confirm that social comments on scientific papers improve the performance of information systems in terms of relevance and novelty.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-05-2022-0283.

Identification and Visualization of Key Topics in Scientific Publications with Transformer-Based Language Models and Document Clustering Methods

With the rapidly growing number of scientific publications, researchers face an increasing challenge of discovering the current research topics and methodologies in a scientific domain. This paper describes an unsupervised topic detection approach that utilizes the new development of transformer-based GPT-3 (Generative Pretrained Transformer 3) similarity embedding models and modern document clustering techniques. In total, 593 publication abstracts across urban study and machine learning domains were used as a case study to demonstrate the three phases of our approach. The iterative clustering phase uses the GPT-3 embeddings to represent the semantic meaning of abstracts and deploys the HDBSCAN (Hierarchical Density-based Spatial Clustering of Applications with Noise) clustering algorithm along with silhouette scores to group similar abstracts. The keyword extraction phase identifies candidate words from each abstract and selects keywords using the Maximal Marginal Relevance ranking algorithm. The keyword grouping phase produces the keyword groups to represent topics in each abstract cluster, again using GPT-3 embeddings, the HDBSCAN algorithm, and silhouette scores. The results are visualized in a web-based interactive tool that allows users to explore abstract clusters and examine the topics in each cluster through keyword grouping. Our unsupervised topic detection approach does not require labeled datasets for training and has the potential to be used in bibliometric analysis in a large collection of publications.

COMPARISON OF LEXRANK ALGORITHM AND MAXIMUM MARGINAL RELEVANCE IN SUMMARY OF INDONESIAN NEWS TEXT IN ONLINE NEWS PORTALS

The presence of online media has shifted print media for news readers to get information that is fast, accurate, and easy to access. However, the problem arises because the length of the news text makes the reader bored to search for the news as a whole so the news that is obtained will be less accurate. For this reason, it is necessary to have an automatic text summary that was raised in this study as well as to compare the Maximum Marginal Relevance (MMR) algorithm and the LexRank algorithm to the summary of Indonesian news texts on the online news portal graphanews. com. the results of the comparison test of text summarization using f-measure , precision and recall show the performance of text summarization with the MMR algorithm is better where f-measure is 91.65%, precision is 91.08% and recall is 92.23%.

A Review on Text Summarization Techniques

Abstract: In recent years, an enormous amount of text data from diversified sources has been emerged day-by-day. This huge amount of data carries essential information and knowledge that needs to be effectively summarized to be useful.We first introduce some concepts related to extractive text summarization and then provide a systematic analysis of various text summarization techniques. In particular, some challenges in extractive summarization of single as well as multiple documents are introduced. The problems focus on the textual assessment and similarity measurement between the text documents are addressed. The challenges discussed are generic and applicable to every possible scenario in text summarization. Then, existing state-of-the-art of extractive summarization techniques are discussed that focus on the identified challenges. Index Terms: Summarization, Graph based summarization, Meta-heuristic based summarization, Maximal marginal relevance based summarization, Evaluation

İlgi Sıralamalarının Artırımlı Olarak Geliştirilmesi: Pennant Erişimle Desteklenen Yeni Bir Yöntem Önerisi

Purpose: Relevance ranking algorithms rank retrieved documents based on the degrees of topical similarity (relevance) between search queries and documents. This paper aims to introduce a new relevance ranking method combining a probabilistic topic modeling algorithm with the “pennant retrieval” method using citation data. Data and Method: We applied this method to the iSearch corpus consisting of c. 435,000 physics papers. We first ran the topic modeling algorithm on titles and summaries of all papers for 65 search queries and obtained the relevance ranking lists. We then used the pennant retrieval to fuse the citation data with the existing relevance rankings, thereby incrementally refining the results. The outcome produced better relevance rankings with papers covering various aspects of the topic searched as well as the more marginal ones. The Maximal Marginal Relevance (MMR) algorithm was used to evaluate the retrieval performance of the proposed method by finding out its effect on relevance ranking algorithms that we used. Findings: Findings suggest that the terms used in different contexts in the papers might sometimes be overlooked by the topic modeling algorithm. Yet, the fusion of citation data to relevance ranking lists provides additional contextual information, thereby further enriching the results with diverse (interdisciplinary) papers of higher relevance. Moreover, results can easily be re-ranked and personalized. Implications: We argue that once it is tested on dynamic corpora for computational load, robustness, replicability, and scalability, the proposed method can in time be used in both local and international information systems such as TR-Dizin, Web of Science, and Scopus. Originality: The proposed method is, as far as we know, the first one that shows that relevance rankings produced with a topic modeling algorithm can be incrementally refined using pennant retrieval techniques based on citation data.

APLIKASI PERINGKASAN DOKUMEN MENGGUNAKAN METODE MAXIMUM MARGINAL RELEVANCE (MMR)

making a summary application to help readers who do not like to read long and thick news articles which take a relatively long time and can cause readers to be lazy to read the news articles. This summary application is used to summarize news articles, in making the application using ASP.Net. In this summary, the Maximum Marginal Relevance (MMR) method is used. In this study, you can use articles on the website, and do it. Articles are processed in the form of a file (single document) with a txt extension. The summary process goes through the preprocessing stage, which consists of sentence segmentation, case folding, tokenizing, filtering, stemming.

Social Computing to Create Government Public Policy Document Blueprint Draft Based on Social Media Data About Covid-19 Using LSTM and MMR Hybrid Algorithms

Abstract- Determining a policy is often limited in a short time so that decisions are prone to inaccuracies and are ultimately judged to be less targeted. Therefore, there is a necessity to use data mining technology. Currently, especially due to the continuously increasing case of the spread of COVID-19 in Indonesia, in order to reduce the rate of spread of COVID-19, the government has established a COVID-19 vaccination and emergency Community Activity Restriction Implementation (PPKM) policies. For the success of the policies, the government is required to ascertain and understand the attitude of the society. Hence, the policies can be accepted and supported by the society. YouTube is one of the sources to discover people’s attitudes because in YouTube, people can express their opinions freely. In this study, a model based on Natural Language Processing (NLP) with the Deep Learning method was developed to analyze people’s attitudes from their writings or posts on social media. As for the algorithm stages, first the model analysis was created using the Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM) algorithms as a comparison. In the COVID-19 vaccination policy, the Bi-LSTM algorithm provided a better evaluation value, i.e., the accuracy value of 87.20%, recall of 87.14%, precision of 87.14%, and F1-score of 87.14%. In the emergency PPKM policy, the LSTM algorithm provided a better evaluation value of 95.13%, recall of 93.94%, precision of 94.08%, and F1-score of 94.01%. In addition, using the Maximum Marginal Relevance (MMR) method to obtain recommendations related to the COVID-19 vaccination policy, the result showed that the government needs to carry out re-socialization regarding vaccination and the impact of the vaccine so that the society can become more cooperative and the emergency PPKM policy needs to be reviewed because it has an impact on the society’s economy.

A Novel Framework using Zero Shot Learning Technique for Non-Factoid Question Answering System

Non-Factoid Question Answering (QA) is the next generation of textual QA systems, which gives passage level summaries for a natural language query, posted by the user. The main issue lies in the appropriateness of the generated summary. This paper proposes a framework for non-factoid QA system, which has three main components: (i) A deep neural network classifier, which produces sentence vector considering word correlation and context. (ii) Zero shot classifier that uses a multi-channel Convolutional Neural Network (CNN), to extract knowledge from multiple sources in the knowledge accumulator. This output acts as a knowledge enhancer that strengthens the passage level summary. (iii) Summary generator that uses Maximal Marginal Relevance (MMR) algorithm, which computes similarity among the query related answer and the sentences from zero shot classifier. This model is applied on the datasets WikiPassageQA and ANTIQUE. The experimental analysis shows that this model gives comparatively better results for WikiPassageQA dataset.

Single document summarization using the information from documents with the same topic

The essence of extractive summarization is to measure the importance of sentences in the document. When extracting summary from a single document, it is difficult to comprehensively and effectively evaluate the importance of sentences due to the lack of information. In this paper, we propose a kind of single document summarization method using information from documents under the same topic. This method integrates the topic information from neighborhood documents and statistical information from the target document to calculate the score of sentences. Then the scoring results are used as a prior scores for each sentence in the target document. After the target document is represented by the sentence graph, the final score of the sentences are obtained by the biased random walk algorithm. Finally, the Maximal Marginal Relevance (MMR) algorithm is used to select the sentences to form summary. The experimental results on the DUC2001 and DUC2002 datasets show that the effect of extracting summary is improved by incorporating information from the documents under the same topic.

A Novel Framework Using Zero Shot Learning Technique for a Non-Factoid Question Answering System

Non-Factoid Question Answering (QA) is the next generation of textual QA systems, which gives passage level summaries for a natural language query, posted by the user. The main issue lies in the appropriateness of the generated summary. This paper proposes a framework for non-factoid QA system, which has three main components: (i) A deep neural network classifier, which produces sentence vector considering word correlation and context. (ii) Zero shot classifier that uses a multi-channel Convolutional Neural Network (CNN), to extract knowledge from multiple sources in the knowledge accumulator. This output acts as a knowledge enhancer that strengthens the passage level summary. (iii) Summary generator that uses Maximal Marginal Relevance (MMR) algorithm, which computes similarity among the query related answer and the sentences from zero shot classifier. This model is applied on the datasets WikiPassageQA and ANTIQUE. The experimental analysis shows that this model gives comparatively better results for WikiPassageQA dataset.

An interactive query-based approach for summarizing scientific documents

PurposeQuery-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.Design/methodology/approachThis 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.FindingsThe 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.Originality/valueThe 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.

A HYBRID MODEL USING THE PRETRAINED BERT AND DEEP NEURAL NETWORKS WITH RICH FEATURE FOR EXTRACTIVE TEXT SUMMARIZATION

Deep neural networks have been applied successfully to extractive text summarization tasks with the accompany of large training datasets. However, when the training dataset is not large enough, these models reveal certain limitations that affect the quality of the system’s summary. In this paper, we propose an extractive summarization system basing on a Convolutional Neural Network and a Fully Connected network for sentence selection. The pretrained BERT multilingual model is used to generate embeddings vectors from the input text. These vectors are combined with TF-IDF values to produce the input of the text summarization system. Redundant sentences from the output summary are eliminated by the Maximal Marginal Relevance method. Our system is evaluated with both English and Vietnamese languages using CNN and Baomoi datasets, respectively. Experimental results show that our system achieves better results comparing to existing works using the same dataset. It confirms that our approach can be effectively applied to summarize both English and Vietnamese languages.