Search Results for « Automatic Document Summarization »

A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.

Current research in automatic single-document summarization is dominated by two effective, yet naïve approaches: summarization by sentence extraction and headline generation via bagof-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techniques have been developed to extract appropriate training data for them from existing document/abstract and document/ headline corpora. We believe that future progress in automatic summarization will be driven both by the development of more sophisticated, linguistically informed models, as well as a more effective leveraging of document/abstract corpora. In order to open the doors to simultaneously achieving both of these goals, we have developed techniques for automatically producing word-to-word and phrase-to-phrase alignments between documents and their human-written abstracts. These alignments make explicit the correspondences that exist in such document/abstract pairs and create a potentially rich data source from which complex summarization algorithms may learn. This paper describes experiments we have carried out to analyze the ability of humans to perform such alignments, and based on these analyses, we describe experiments for creating them automatically. Our model for the alignment task is based on an extension of the standard hidden Markov model and learns to create alignments in a completely unsupervised fashion. We describe our model in detail and present experimental results that show that our model is able to learn to reliably identify word- and phrase-level alignments in a corpus of (document, abstract) pairs.

Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes domains like healthcare, law, and finance. In this work, we introduce Conformal Importance Summarization, the first framework for importance-preserving summary generation which uses conformal prediction to provide rigorous, distribution-free coverage guarantees. By calibrating thresholds on sentence-level importance scores, we enable extractive document summarization with user-specified coverage and recall rates over critical content. Our method is model-agnostic, requires only a small calibration set, and seamlessly integrates with existing black-box LLMs. Experiments on established summarization benchmarks demonstrate that Conformal Importance Summarization achieves the theoretically assured information coverage rate. Our work suggests that Conformal Importance Summarization can be combined with existing techniques to achieve reliable, controllable automatic summarization, paving the way for safer deployment of AI summarization tools in critical applications. Code is available at https://github.com/layer6ai-labs/conformal-importance-summarization.

Herkömmliche Suchmaschinen filtern die großen Mengen im Internet verfügbarer Daten durch die Abbildung einer Nutzer-Suchanfrage auf eine potentiell große Menge von Dokumenten. Das Auffinden der gesuchten Informationen innerhalb dieser Dokumente bleibt jedoch Aufgabe des Nutzers. Daher ist die Entwicklung computergestützten Methoden essentiell, welche über herkömmliche, dokumentenzentrische Informationsbeschaffungslösungen hinausgehen, und die den Nutzer bei der Verarbeitung großer Dokumentenmengen und darin enthaltener Informationen unterstützen. Automatisierte Textzusammenfassung ist eine solche Technologie, da Zusammenfassungen konzise die Kernpunkte wesentlich größerer Quelltexte zusammentragen und dabei irrelevante und redundante Informationen herausfiltern. Textzusammenfassungssysteme können also ein mächtiges Werkzeug zur Reduktion der von einem Nutzer zu verarbeitenden Datenmengen darstellen. Im Rahmen dieser Arbeit werden Algorithmen zur personalisierten Zusammenfassung von Kollektionen thematisch aufeinander bezogener Nachrichtenartikel entworfen und evaluiert. Von speziellem Interesse ist hierbei die Identifikation der Unterthemen, die das übergeordnete Hauptthema einer solchen Kollektion strukturieren, da dieses die Bestimmung wesentlicher Inhalte und die Erkennung von Redundanzen erleichtert. Existierende Modellierungsverfahren berücksichtigen nicht in ausreichendem Maße die Mehrdeutigkeit natürlicher Sprache und die Begrenztheit von Satzvokabularen. Die in dieser Arbeit entwickelten Algorithmen hingegen werten Wortkontextinformationen zur Themenerkennung aus, und profitieren von den dadurch gegebenen Zusatzinformationen bei der Erstellung personalisierter Zusammenfassungen. Ausführliche Tests in verschiedenen Szenarien und für unterschiedliche Datensätze zeigen, dass die entwickelten Lösungen Zusammenfassungen von höherer Qualität liefern als existierende Ansätze. Nachrichtenartikel, die über ein bestimmtes Ereignis berichten, sind nicht nur ähnlich in Hinblick auf ihre Unterthemen, sondern enthalten auch oft die gleichen Fakten. Die Erkennung ähnlicher Fakten ist eine wünschenswerte, aber derzeit ungelöste Teilaufgabe von Zusammenfassungssystemen, da eine Bewertung der semantischen Ähnlichkeit von Teilsätzen nicht mit der benötigten Präzision möglich ist. Einen weiteren Schwerpunkt dieser Arbeit bilden daher eine ausführliche Analyse von faktenähnlichen Satzabschnitten in Nachrichtenartikeln und Referenzzusammenfassungen, sowie die Entwicklung eines Algorithmus zur Erkennung ähnlicher Teilsätze.

Despite the prevalence of pretrained language models in natural language understanding tasks, understanding lengthy text such as document is still challenging due to the data sparseness problem. Inspired by that humans develop their ability of understanding lengthy text from reading shorter text, we propose a simple yet effective summarization-based data augmentation, SUMMaug, for document classification. We first obtain easy-to-learn examples for the target document classification task by summarizing the input of the original training examples, while optionally merging the original labels to conform to the summarized input. We then use the generated pseudo examples to perform curriculum learning. Experimental results on two datasets confirmed the advantage of our method compared to existing baseline methods in terms of robustness and accuracy. We release our code and data at https://github.com/etsurin/summaug.

Document summarization is the process of generating the summary of the documents gathered from the web sources. It reduces the burden of web readers by reducing the necessity of reading the entire document contents by generating the short summary. In our previous research work this is performed by introducing the method namely Noun weight based Automated Multi-Document Summarization method (NW-AMDSM). However the previous research work doesn’t concentrate on the semantic similarity which might reduce the accuracy of the summarization outcome. This is resolved in the proposed research method by introducing the method namely Semantic Similarity based Automatic Document Summarization Method (SS-ADSM). In this research work, multi document grouping is done is based on semantic similarity computation, thus the document with similar contents can be grouped more accurately. Here the semantic similarity computation is performed with the help of word net analyzer. The document grouping is done by introducing the modified FCM clustering algorithm. Finally hybrid neuro fuzzy genetic algorithm is introduced to perform the automatic summarization. The numerical analysis of the proposed research method is conducted in the matlab simulation environment and compared with other research methods in terms various performance metrics. The simulation analysis proved proposed method tends to have better performance in terms of increased accuracy of document summarization outcome.

The centroid-based model for extractive document summarization is a simple and fast baseline that ranks sentences based on their similarity to a centroid vector. In this paper, we apply this ranking to possible summaries instead of sentences and use a simple greedy algorithm to find the best summary. Furthermore, we show possi- bilities to scale up to larger input docu- ment collections by selecting a small num- ber of sentences from each document prior to constructing the summary. Experiments were done on the DUC2004 dataset for multi-document summarization. We ob- serve a higher performance over the orig- inal model, on par with more complex state-of-the-art methods.

Actual problem in nowadays is to efficiently process the large amount of data that pass through our mind everyday. The object of study of this paper is automatic summarization algorithms. The main goal is to implement and make comparison of different summarization techniques on corpora of news articles parsed from the web. This research work contains the description of three summarization techniques based on TextRank algorithm: General TextRank, BM25, LongestCommonSubstring. It is specially noted the languages of used corpora: Russian and Kazakh languages. The results of summarization processes and their comparison are provided. It should be emphasized that used algorithms are well-known, but the way of their evaluation on defined corpora is different from those which usually used in summary evaluation. The method of summary evaluation proposed use the special dictionary of extracted key-words on the topic of corpora. As the title implies the article describes applying statistical information. The semantic and syntactic features of text are not examined.

The centroid method is a simple approach for extractive multi-document summarization and many improvements to its pipeline have been proposed. We further refine it by adding a beam search process to the sentence selection and also a centroid estimation attention model that leads to improved results. We demonstrate this in several multi-document summarization datasets, including in a multilingual scenario.

In this paper, we propose a automatic document summarization method based on Principal Component Analysis(PCA) which is one of the multivariate statistical methods. After extracting thematic words using PCA, we select the statements containing the respective extracted thematic words, and make the document summary with them. Experimental results using newspaper articles show that the proposed method is superior to the method using either word frequency or information retrieval thesaurus.