首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 399 毫秒
1.
Opinion summarization can facilitate user’s decision-making by mining the salient review information. However, due to the lack of sufficient annotated data, most of the early works are based on extractive methods, which restricts the performance of opinion summarization. In this work, we aim to improve the informativeness of opinion summarization to provide better guidance to users. We consider the setting with only reviews without corresponding summaries, and propose an aspect-augmented model for unsupervised abstractive opinion summarization, denoted as AsU-OSum. We first employ an aspect-based sentiment analysis system to extract opinion phrases from reviews. Then, we construct a heterogeneous graph consisting of reviews and opinion clusters as nodes, which is used to enhance the Transformer-based encoder–decoder framework. Furthermore, we design a novel cascaded attention mechanism to prompt the decoder to pay more attention to the aspects that are more likely to appear in summary. During training, we introduce a sentiment accuracy reward that further enhances the learning ability of our model. We conduct comprehensive experiments on the Yelp, Amazon, and Rotten Tomatoes datasets. Automatic evaluation results show that our model is competitive and performs better than the state-of-the-art (SOTA) models on some ROUGE metrics. Human evaluation results further verify that our model can generate more informative summaries and reduce redundancy.  相似文献   

2.
Automated summaries help tackle the ever growing volume of information floating around. There are two broad categories: extract and abstract. In the former we retain the more important sentences more or less in their original structure, while the latter requires a fusion of multiple sentences and/or paraphrasing. This is a more challenging task than extract summaries. In this paper, we present a novel generic abstract summarizer for a single document in Arabic language. The system starts by segmenting the input text topic wise. Then, each textual segment is extractively summarized. Finally, we apply rule-based sentence reduction technique. The RST-based extractive summarizer is an enhanced version of the system in Azmi and Al-Thanyyan (2012). By controlling the size of the extract summary of each segment we can cap the size of the final abstractive summary. Both summarizers, the enhanced extractive and the abstractive, were evaluated. We tested our enhanced extractive summarizer on the same dataset in the aforementioned paper, using the measures recall, precision and Rouge. The results show noticeable improvement in the performance, specially the precision in shorter summaries. The abstractive summarizer was tested on a set of 150 documents, generating summaries of sizes 50%, 40%, 30% and 20% (of the original’s word count). The results were assessed by two human experts who graded them out of a maximum score of 5. The average score ranged between 4.53 and 1.92 for summaries at different granularities, with shorter summaries receiving the lower score. The experimental results are encouraging and demonstrate the effectiveness of our approach.  相似文献   

3.
Recently, the Transformer model architecture and the pre-trained Transformer-based language models have shown impressive performance when used in solving both natural language understanding and text generation tasks. Nevertheless, there is little research done on using these models for text generation in Arabic. This research aims at leveraging and comparing the performance of different model architectures, including RNN-based and Transformer-based ones, and different pre-trained language models, including mBERT, AraBERT, AraGPT2, and AraT5 for Arabic abstractive summarization. We first built an Arabic summarization dataset of 84,764 high-quality text-summary pairs. To use mBERT and AraBERT in the context of text summarization, we employed a BERT2BERT-based encoder-decoder model where we initialized both the encoder and decoder with the respective model weights. The proposed models have been tested using ROUGE metrics and manual human evaluation. We also compared their performance on out-of-domain data. Our pre-trained Transformer-based models give a large improvement in performance with ～79% less data. We found that AraT5 scores ～3 ROUGE higher than a BERT2BERT-based model that is initialized with AraBERT, indicating that an encoder-decoder pre-trained Transformer is more suitable for summarizing Arabic text. Also, both of these two models perform better than AraGPT2 by a clear margin, which we found to produce summaries with high readability but with relatively lesser quality. On the other hand, we found that both AraT5 and AraGPT2 are better at summarizing out-of-domain text. We released our models and dataset publicly1,.2  相似文献   

4.
The increasing volume of textual information on any topic requires its compression to allow humans to digest it. This implies detecting the most important information and condensing it. These challenges have led to new developments in the area of Natural Language Processing (NLP) and Information Retrieval (IR) such as narrative summarization and evaluation methodologies for narrative extraction. Despite some progress over recent years with several solutions for information extraction and text summarization, the problems of generating consistent narrative summaries and evaluating them are still unresolved. With regard to evaluation, manual assessment is expensive, subjective and not applicable in real time or to large collections. Moreover, it does not provide re-usable benchmarks. Nevertheless, commonly used metrics for summary evaluation still imply substantial human effort since they require a comparison of candidate summaries with a set of reference summaries. The contributions of this paper are three-fold. First, we provide a comprehensive overview of existing metrics for summary evaluation. We discuss several limitations of existing frameworks for summary evaluation. Second, we introduce an automatic framework for the evaluation of metrics that does not require any human annotation. Finally, we evaluate the existing assessment metrics on a Wikipedia data set and a collection of scientific articles using this framework. Our findings show that the majority of existing metrics based on vocabulary overlap are not suitable for assessment based on comparison with a full text and we discuss this outcome.  相似文献   

5.
Centroid-based summarization of multiple documents   总被引：2，自引：0，他引：2  
We present a multi-document summarizer, MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We describe two new techniques, a centroid-based summarizer, and an evaluation scheme based on sentence utility and subsumption. We have applied this evaluation to both single and multiple document summaries. Finally, we describe two user studies that test our models of multi-document summarization.  相似文献   

6.
Text simplification and text summarisation are related, but different sub-tasks in Natural Language Generation. Whereas summarisation attempts to reduce the length of a document, whilst keeping the original meaning, simplification attempts to reduce the complexity of a document. In this work, we combine both tasks of summarisation and simplification using a novel hybrid architecture of abstractive and extractive summarisation called HTSS. We extend the well-known pointer generator model for the combined task of summarisation and simplification. We have collected our parallel corpus from the simplified summaries written by domain experts published on the science news website EurekaAlert (www.eurekalert.org). Our results show that our proposed HTSS model outperforms neural text simplification (NTS) on SARI score and abstractive text summarisation (ATS) on the ROUGE score. We further introduce a new metric (CSS1) which combines SARI and Rouge and demonstrates that our proposed HTSS model outperforms NTS and ATS on the joint task of simplification and summarisation by 38.94% and 53.40%, respectively. We provide all code, models and corpora to the scientific community for future research at the following URL: https://github.com/slab-itu/HTSS/.  相似文献   

7.
Text summarization is a process of generating a brief version of documents by preserving the fundamental information of documents as much as possible. Although most of the text summarization research has been focused on supervised learning solutions, there are a few datasets indeed generated for summarization tasks, and most of the existing summarization datasets do not have human-generated goal summaries which are vital for both summary generation and evaluation. Therefore, a new dataset was presented for abstractive and extractive summarization tasks in this study. This dataset contains academic publications, the abstracts written by the authors, and extracts in two sizes, which were generated by human readers in this research. Then, the resulting extracts were evaluated to ensure the validity of the human extract production process. Moreover, the extractive summarization problem was reinvestigated on the proposed summarization dataset. Here the main point taken into account was to analyze the feature vector to generate more informative summaries. To that end, a comprehensive syntactic feature space was generated for the proposed dataset, and the impact of these features on the informativeness of the resulting summary was investigated. Besides, the summarization capability of semantic features was experienced by using GloVe and word2vec embeddings. Finally, the use of ensembled feature space, which corresponds to the joint use of syntactic and semantic features, was proposed on a long short-term memory-based neural network model. ROUGE metrics evaluated the model summaries, and the results of these evaluations showed that the use of the proposed ensemble feature space remarkably improved the single-use of syntactic or semantic features. Additionally, the resulting summaries of the proposed approach on ensembled features prominently outperformed or provided comparable performance than summaries obtained by state-of-the-art models for extractive summarization.  相似文献   

8.
In recent years, there has been increased interest in topic-focused multi-document summarization. In this task, automatic summaries are produced in response to a specific information request, or topic, stated by the user. The system we have designed to accomplish this task comprises four main components: a generic extractive summarization system, a topic-focusing component, sentence simplification, and lexical expansion of topic words. This paper details each of these components, together with experiments designed to quantify their individual contributions. We include an analysis of our results on two large datasets commonly used to evaluate task-focused summarization, the DUC2005 and DUC2006 datasets, using automatic metrics. Additionally, we include an analysis of our results on the DUC2006 task according to human evaluation metrics. In the human evaluation of system summaries compared to human summaries, i.e., the Pyramid method, our system ranked first out of 22 systems in terms of overall mean Pyramid score; and in the human evaluation of summary responsiveness to the topic, our system ranked third out of 35 systems.  相似文献   

9.
Incorporating topic information can help response generation models to produce informative responses for chat-bots. Previous work only considers the individual semantic of each topic, ignoring its specific dialog context, which may result in inaccurate topic representation and hurt response coherence. Besides, as an important feature of multi-turn conversation, dynamic topic transitions have not been well-studied. We propose a Context-Controlled Topic-Aware neural response generation model, i.e., CCTA, which makes dialog context interact with the process of topic representing and transiting to achieve balanced improvements on response informativeness and contextual coherence. CCTA focuses on capturing the semantical relations within topics as well as their corresponding contextual information in conversation, to produce context-dependent topic representations at the word-level and turn-level. Besides, CCTA introduces a context-controlled topic transition strategy, utilizing contextual topics to yield relevant transition words. Extensive experimental results on two benchmark multi-turn conversation datasets validate the superiority of our proposal on generating coherent and informative responses against the state-of-the-art baselines. We also find that topic transition modeling can work as an auxiliary learning task to boost the response generation.  相似文献   

10.
Topic models are widely used for thematic structure discovery in text. But traditional topic models often require dedicated inference procedures for specific tasks at hand. Also, they are not designed to generate word-level semantic representations. To address the limitations, we propose a neural topic modeling approach based on the Generative Adversarial Nets (GANs), called Adversarial-neural Topic Model (ATM) in this paper. To our best knowledge, this work is the first attempt to use adversarial training for topic modeling. The proposed ATM models topics with dirichlet prior and employs a generator network to capture the semantic patterns among latent topics. Meanwhile, the generator could also produce word-level semantic representations. Besides, to illustrate the feasibility of porting ATM to tasks other than topic modeling, we apply ATM for open domain event extraction. To validate the effectiveness of the proposed ATM, two topic modeling benchmark corpora and an event dataset are employed in the experiments. Our experimental results on benchmark corpora show that ATM generates more coherence topics (considering five topic coherence measures), outperforming a number of competitive baselines. Moreover, the experiments on event dataset also validate that the proposed approach is able to extract meaningful events from news articles.  相似文献   

11.
A new approach to narrative abstractive summarization (NATSUM) is presented in this paper. NATSUM is centered on generating a narrative chronologically ordered summary about a target entity from several news documents related to the same topic. To achieve this, first, our system creates a cross-document timeline where a time point contains all the event mentions that refer to the same event. This timeline is enriched with all the arguments of the events that are extracted from different documents. Secondly, using natural language generation techniques, one sentence for each event is produced using the arguments involved in the event. Specifically, a hybrid surface realization approach is used, based on over-generation and ranking techniques. The evaluation demonstrates that NATSUM performed better than extractive summarization approaches and competitive abstractive baselines, improving the F1-measure at least by 50%, when a real scenario is simulated.  相似文献   

12.
In this paper, we propose a novel approach to automatic generation of summary templates from given collections of summary articles. We first develop an entity-aspect LDA model to simultaneously cluster both sentences and words into aspects. We then apply frequent subtree pattern mining on the dependency parse trees of the clustered and labeled sentences to discover sentence patterns that well represent the aspects. Finally, we use the generated templates to construct summaries for new entities. Key features of our method include automatic grouping of semantically related sentence patterns and automatic identification of template slots that need to be filled in. Also, we implement a new sentence compression algorithm which use dependency tree instead of parser tree. We apply our method on five Wikipedia entity categories and compare our method with three baseline methods. Both quantitative evaluation based on human judgment and qualitative comparison demonstrate the effectiveness and advantages of our method.  相似文献   

13.
Existing pseudo-relevance feedback (PRF) methods often divide an original query into individual terms for processing and select expansion terms based on the term frequency, proximity, position, etc. This process may lose some contextual semantic information from the original query. In this work, based on the classic Rocchio model, we propose a probabilistic framework that incorporates sentence-level semantics via Bidirectional Encoder Representations from Transformers (BERT) into PRF. First, we obtain the importance of terms at the term level. Then, we use BERT to interactively encode the query and sentences in the feedback document to acquire the semantic similarity score of a sentence and the query. Next, the semantic scores of different sentences are summed as the term score at the sentence level. Finally, we balance the term-level and sentence-level weights by adjusting factors and combine the terms with the top-k scores to form a new query for the next-round processing. We apply this method to three Rocchio-based models (Rocchio, PRoc2, and KRoc). A series of experiments are conducted based on six official TREC data sets. Various evaluation indicators suggest that the improved models achieve a significant improvement over the corresponding baseline models. Our proposed models provide a promising avenue for incorporating sentence-level semantics into PRF, which is feasible and robust. Through comparison and analysis of a case study, expansion terms obtained from the proposed models are shown to be more semantically consistent with the query.  相似文献   

14.
Most knowledge accumulated through scientific discoveries in genomics and related biomedical disciplines is buried in the vast amount of biomedical literature. Since understanding gene regulations is fundamental to biomedical research, summarizing all the existing knowledge about a gene based on literature is highly desirable to help biologists digest the literature. In this paper, we present a study of methods for automatically generating gene summaries from biomedical literature. Unlike most existing work on automatic text summarization, in which the generated summary is often a list of extracted sentences, we propose to generate a semi-structured summary which consists of sentences covering specific semantic aspects of a gene. Such a semi-structured summary is more appropriate for describing genes and poses special challenges for automatic text summarization. We propose a two-stage approach to generate such a summary for a given gene – first retrieving articles about a gene and then extracting sentences for each specified semantic aspect. We address the issue of gene name variation in the first stage and propose several different methods for sentence extraction in the second stage. We evaluate the proposed methods using a test set with 20 genes. Experiment results show that the proposed methods can generate useful semi-structured gene summaries automatically from biomedical literature, and our proposed methods outperform general purpose summarization methods. Among all the proposed methods for sentence extraction, a probabilistic language modeling approach that models gene context performs the best.  相似文献   

15.
We present a new paradigm for the automatic creation of document headlines that is based on direct transformation of relevant textual information into well-formed textual output. Starting from an input document, we automatically create compact representations of weighted finite sets of strings, called WIDL-expressions, which encode the most important topics in the document. A generic natural language generation engine performs the headline generation task, driven by both statistical knowledge encapsulated in WIDL-expressions (representing topic biases induced by the input document) and statistical knowledge encapsulated in language models (representing biases induced by the target language). Our evaluation shows similar performance in quality with a state-of-the-art, extractive approach to headline generation, and significant improvements in quality over previously proposed solutions to abstractive headline generation.  相似文献   

16.
Extractive summarization for academic articles in natural sciences and medicine has attracted attention for a long time. However, most existing extractive summarization models often process academic articles with sentence classification models, which are hard to produce comprehensive summaries. To address this issue, we explore a new view to solve the extractive summarization of academic articles in natural sciences and medicine by taking it as a question-answering process. We propose a novel framework, MRC-Sum, where the extractive summarization for academic articles in natural sciences and medicine is cast as an MRC (Machine Reading Comprehension) task. To instantiate MRC-Sum, article-summary pairs in the summarization datasets are firstly reconstructed into (Question, Answer, Context) triples in the MRC task. Several questions are designed to cover the main aspects (e.g. Background, Method, Result, Conclusion) of the articles in natural sciences and medicine. A novel strategy is proposed to solve the problem of the non-existence of the ground truth answer spans. Then MRC-Sum is trained on the reconstructed datasets and large-scale pre-trained models. During the inference stage, four answer spans of the predefined questions are given by MRC-Sum and concatenated to form the final summary for each article. Experiments on three publicly available benchmarks, i.e., the Covid, PubMed, and arXiv datasets, demonstrate the effectiveness of MRC-Sum. Specifically, MRC-Sum outperforms advanced extractive summarization baselines on the Covid dataset and achieves competitive results on the PubMed and arXiv datasets. We also propose a novel metric, COMPREHS, to automatically evaluate the comprehensiveness of the system summaries for academic articles in natural sciences and medicine. Abundant experiments are conducted and verified the reliability of the proposed metric. And the results of the COMPREHS metric show that MRC-Sum is able to generate more comprehensive summaries than the baseline models.  相似文献   

17.
A well-known challenge for multi-document summarization (MDS) is that a single best or “gold standard” summary does not exist, i.e. it is often difficult to secure a consensus among reference summaries written by different authors. It therefore motivates us to study what the “important information” is in multiple input documents that will guide different authors in writing a summary. In this paper, we propose the notions of macro- and micro-level information. Macro-level information refers to the salient topics shared among different input documents, while micro-level information consists of different sentences that act as elaborating or provide complementary details for those salient topics. Experimental studies were conducted to examine the influence of macro- and micro-level information on summarization and its evaluation. Results showed that human subjects highly relied on macro-level information when writing a summary. The length allowed for summaries is the leading factor that affects the summary agreement. Meanwhile, our summarization evaluation approach based on the proposed macro- and micro-structure information also suggested that micro-level information offered complementary details for macro-level information. We believe that both levels of information form the “important information” which affects the modeling and evaluation of automatic summarization systems.  相似文献   

18.
In this paper, we present a topic discovery system aimed to reveal the implicit knowledge present in news streams. This knowledge is expressed as a hierarchy of topic/subtopics, where each topic contains the set of documents that are related to it and a summary extracted from these documents. Summaries so built are useful to browse and select topics of interest from the generated hierarchies. Our proposal consists of a new incremental hierarchical clustering algorithm, which combines both partitional and agglomerative approaches, taking the main benefits from them. Finally, a new summarization method based on Testor Theory has been proposed to build the topic summaries. Experimental results in the TDT2 collection demonstrate its usefulness and effectiveness not only as a topic detection system, but also as a classification and summarization tool.  相似文献   

19.
Generating news headlines has been one of the predominant problems in Natural Language Processing research. Modern transformer models, if fine-tuned, can present a good headline with attention to all the parts of a disaster-news article. A disaster-news headline generally focuses on the event, its effect, and the major impacts, which a transformer model lacks when generating the headline. The extract-then-abstract based method proposed in this article improves the performance of a state-of-the-art transformer abstractor to generate a good-quality disaster-news headline. In this work, a Deep Neural Network (DNN) based sentence extractor and a transformer-based abstractive summarizer work sequentially to generate a headline. The sentence extraction task is formulated as a binary classification problem where the DNN model is trained to generate two binary labels: one corresponding to the sentence similarity with ground truth headlines and the other corresponding to the presence of disaster and its impact related information in the sentence. The transformer model generates the headline from the sentences extracted by the DNN. ROUGE scores of the headlines generated using the proposed method are found to be better than the scores of the headlines generated directly from the original documents. The highest ROUGE 1, 2, and 3 score improvements are observed in the case of the Text-To-Text Transfer Transformer (T5) model by 17.85%, 38.13%, and 21.01%, respectively. Such improvements suggest that the proposed method can have a high utility for finding effective headlines from disaster related news articles.  相似文献   

20.
Text mining techniques for patent analysis   总被引：1，自引：0，他引：1  
Patent documents contain important research results. However, they are lengthy and rich in technical terminology such that it takes a lot of human efforts for analyses. Automatic tools for assisting patent engineers or decision makers in patent analysis are in great demand. This paper describes a series of text mining techniques that conforms to the analytical process used by patent analysts. These techniques include text segmentation, summary extraction, feature selection, term association, cluster generation, topic identification, and information mapping. The issues of efficiency and effectiveness are considered in the design of these techniques. Some important features of the proposed methodology include a rigorous approach to verify the usefulness of segment extracts as the document surrogates, a corpus- and dictionary-free algorithm for keyphrase extraction, an efficient co-word analysis method that can be applied to large volume of patents, and an automatic procedure to create generic cluster titles for ease of result interpretation. Evaluation of these techniques was conducted. The results confirm that the machine-generated summaries do preserve more important content words than some other sections for classification. To demonstrate the feasibility, the proposed methodology was applied to a real-world patent set for domain analysis and mapping, which shows that our approach is more effective than existing classification systems. The attempt in this paper to automate the whole process not only helps create final patent maps for topic analyses, but also facilitates or improves other patent analysis tasks such as patent classification, organization, knowledge sharing, and prior art searches.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号