Generic Summaries Research Articles

Document Summarization with Latent Queries

AbstractThe availability of large-scale datasets has driven the development of neural models that create generic summaries for single or multiple documents. For query-focused summarization (QFS), labeled training data in the form of queries, documents, and summaries is not readily available. We provide a unified modeling framework for any kind of summarization, under the assumption that all summaries are a response to a query, which is observed in the case of QFS and latent in the case of generic summarization. We model queries as discrete latent variables over document tokens, and learn representations compatible with observed and unobserved query verbalizations. Our framework formulates summarization as a generative process, and jointly optimizes a latent query model and a conditional language model. Despite learning from generic summarization data only, our approach outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.1

Convex Aggregation for Opinion Summarization

Recent advances in text autoencoders have significantly improved the quality of the latent space, which enables models to generate grammatical and consistent text from aggregated latent vectors. As a successful application of this property, unsupervised opinion summarization models generate a summary by decoding the aggregated latent vectors of inputs. More specifically, they perform the aggregation via simple average. However, little is known about how the vector aggregation step affects the generation quality. In this study, we revisit the commonly used simple average approach by examining the latent space and generated summaries. We found that text autoencoders tend to generate overly generic summaries from simply averaged latent vectors due to an unexpected L2-norm shrinkage in the aggregated latent vectors, which we refer to as summary vector degeneration. To overcome this issue, we develop a framework Coop, which searches input combinations for the latent vector aggregation using input-output word overlap. Experimental results show that Coop successfully alleviates the summary vector degeneration issue and establishes new state-of-the-art performance on two opinion summarization benchmarks. Code is available at https://github.com/megagonlabs/coop.

Sentic Computing for Aspect-Based Opinion Summarization Using Multi-Head Attention with Feature Pooled Pointer Generator Network

Neural sequence to sequence models have achieved superlative performance in summarizing text. But they tend to generate generic summaries that under-represent the opinion-sensitive aspects of the document. Additionally, the sequence to sequence models are prone to test-train discrepancy (exposure-bias) arising from the differential summary decoding processes in the training and testing phases. The models use ground truth summary words in the decoder training phase and predicted outputs in the testing phase. This inconsistency leads to error accumulation and substandard performance. To address these gaps, a cognitive aspect-based opinion summarizer, Feature Pooled Pointer Generator Network (FP2GN), is proposed which selectively attends to thematic and contextual cues to generate sentiment-aware review summaries. This study augments the pointer generator framework with opinion feature extraction, feature pooling, and mutual attention mechanism for opinion summarization. The proposed model FP2GN identifies the aspect terms in review text using sentic computing (SenticNet 5 and concept frequency-inverse opinion frequency) and statistical feature engineering. These aspect terms are encoded into context embeddings using weighted average feature pooling, which is processed in a pointer-generator framework inspired stacked Bi-LSTM encoder–decoder model with multi-head self-attention. The decoder system uses temporal and mutual attention mechanisms to ensure the appropriate representation of input-sequence. The study also proffers the use of teacher forcing ratio to curtail the exposure-bias-related error-accumulation. The model achieves ROUGE-1 score of 86.04% and ROUGE-L score of 88.51% on the Amazon Fine Foods dataset. An average gain of 2% over other methods is observed. The proposed model reinforces pointer generator network architecture with opinion feature extraction, feature pooling, and mutual attention mechanism to generate human-readable opinion summaries. Empirical analysis substantiates that the proposed model is better than the baseline opinion summarizers.

Towards Context-Aware Opinion Summarization for Monitoring Social Impact of News

Opinion mining and summarization of the increasing user-generated content on different digital platforms (e.g., news platforms) are playing significant roles in the success of government programs and initiatives in digital governance, from extracting and analyzing citizen’s sentiments for decision-making. Opinion mining provides the sentiment from contents, whereas summarization aims to condense the most relevant information. However, most of the reported opinion summarization methods are conceived to obtain generic summaries, and the context that originates the opinions (e.g., the news) has not usually been considered. In this paper, we present a context-aware opinion summarization model for monitoring the generated opinions from news. In this approach, the topic modeling and the news content are combined to determine the “importance” of opinionated sentences. The effectiveness of different developed settings of our model was evaluated through several experiments carried out over Spanish news and opinions collected from a real news platform. The obtained results show that our model can generate opinion summaries focused on essential aspects of the news, as well as cover the main topics in the opinionated texts well. The integration of term clustering, word embeddings, and the similarity-based sentence-to-news scoring turned out the more promising and effective setting of our model.

Text Summarisation Using Laplacian Centrality-Based Minimum Vertex Cover

Outdegree Centrality (OC) is a graph-based centrality measure that captures local connectedness of a node in a graph. The measure has been used in the literature to highlight key sentences in a graph-based optimisation method for summarisation. It is observed in resultant summaries that OC tends to be biased towards selecting introductory sentences of the document producing only generic summaries. The different graph centrality measures lead to different interpretations of a summary. Therefore, the authors propose to use another suitable centrality measure in order to generate more specific summary rather than a generic summary. Such a summary is expected to be highly informative covering all the subtopics of the source document. This requirement has instigated the authors to use Laplacian Centrality (LC) measure to find the significance of the nodes. The essence of this measure lies in highlighting central nodes from subgraphs which contribute non-uniformly towards the common goal of the graph. The modified method has shown significant improvement in informativeness and coherence of summaries and outperformed state-of-the-art results.

Passage-Based Text Summarization for Legal Information Retrieval

Automatic text summarization is a process of condensing the content of a text document to pursue the most important information. It plays a significant role in various tasks like text categorization, question answering and information retrieval (IR). As legal information retrieval (LIR) is a subfield of IR, the produced summaries are combined into IR system, with the objective of decreasing the length of the document. In this way, we can improve the access time for searching the information, and relevant documents are retrieved. In this article, we present the creation of passage-level summaries (generic and legal) with different compression ratios and evaluate their performance. The generic summaries present the overall description of the essential information of a document and legal summaries, produced by taking into account the domain-specific features that are present in the document. Next, we propose Boosting Okapi BM25 which is the modified model of Okapi BM25 to increase the efficiency of the LIR. We have evaluated proposed LIR approach in terms of MAP and R-precision and summarization approach using ROUGE tool on FIRE2013 and FIRE2014 datasets. To show the efficacy of the proposed system, we compare the experimental results with different IR models like PL2, \(In\_expB2\), \(In\_expC2\), InL2, \(DFR\_BM25\), Okapi BM25 in terms of MAP. The experimental results of the proposed system show better performance than the existing various IR models in terms of various performance metrics. The empirical results also exhibit that the integration of text summarization and IR techniques helps in retrieving relevant information with less access time.

An unsupervised approach to generating generic summaries of documents

We present an optimization-based unsupervised approach to automatic document summarization. In the proposed approach, text summarization is modeled as a Boolean programming problem. This model generally attempts to optimize three properties, namely, (1) relevance: summary should contain informative textual units that are relevant to the user; (2) redundancy: summaries should not contain multiple textual units that convey the same information; and (3) length: summary is bounded in length. The approach proposed in this paper is applicable to both tasks: single- and multi-document summarization. In both tasks, documents are split into sentences in preprocessing. We select some salient sentences from document(s) to generate a summary. Finally, the summary is generated by threading all the selected sentences in the order that they appear in the original document(s). We implemented our model on multi-document summarization task. When comparing our methods to several existing summarization methods on an open DUC2005 and DUC2007 data sets, we found that our method improves the summarization results significantly. This is because, first, when extracting summary sentences, this method not only focuses on the relevance scores of sentences to the whole sentence collection, but also the topic representative of sentences. Second, when generating a summary, this method also deals with the problem of repetition of information. The methods were evaluated using ROUGE-1, ROUGE-2 and ROUGE-SU4 metrics. In this paper, we also demonstrate that the summarization result depends on the similarity measure. Results of the experiment showed that combination of symmetric and asymmetric similarity measures yields better result than their use separately.

Generic speech summarization of transcribed lecture videos: Using tags and their semantic relations

We propose a tag‐based framework that simulates human abstractors' ability to select significant sentences based on key concepts in a sentence as well as the semantic relations between key concepts to create generic summaries of transcribed lecture videos. The proposed extractive summarization method uses tags (viewer‐ and author‐assigned terms) as key concepts. Our method employs Flickr tag clusters and WordNet synonyms to expand tags and detect the semantic relations between tags. This method helps select sentences that have a greater number of semantically related key concepts. To investigate the effectiveness and uniqueness of the proposed method, we compare it with an existing technique, latent semantic analysis (LSA), using intrinsic and extrinsic evaluations. The results of intrinsic evaluation show that the tag‐based method is as or more effective than the LSA method. We also observe that in the extrinsic evaluation, the grand mean accuracy score of the tag‐based method is higher than that of the LSA method, with a statistically significant difference. Elaborating on our results, we discuss the theoretical and practical implications of our findings for speech video summarization and retrieval.

Mnemonic verses in medieval bestiaries

Mnemonic verses were one of the most popular tools for medieval teaching. These verses are attested in all genres of medieval literature, but strangely enough they are rare in medieval bestiaries, which are primarily a didactic genre. My paper will discuss a previously neglected case of one Second Family late thirteenth-century bestiary of English origin, namely Oxford, Bodleian Library MS Bodley 533. Surprisingly, in this manuscript there are eleven sets of verses, mostly quatrains of so-called Leonine hexameters, which represent sui generic summaries for the chapters on various bestiary creatures. The present article discusses for the first time these previously unpublished verses and analyzes their function in the manuscript.

TEXT SUMMARIZATION USING LEXICAL COHESION: APPROACHES AND EVALUATIONS

Popularity of the Internet has contributed towards the explosive growth of online information, and it is especially useful to have tools which can help users digest information content. Text summarization addresses this need by taking a source text, selecting the most important portions of it, and presenting coherent summary to the user in a manner sensitive to the user's or application's needs. The goal of this paper is to show how these objectives can be achieved through an efficient use of lexical cohesion. The current work addresses both generic and query-based summaries in the context of single documents and sets of documents as in current news. We present an approach for identifying the most important portions of the text which are topically best suited to represent the source texts according to the author's views or in response to the user's interests. This identification must also take into consideration the degree of connectiveness among the chosen text portions so as to minimize the danger of producing summaries which contain poorly linked sentences. We present a system that handles these objectives, discuss its performance, and evaluate it and compare it to other systems in the context of Document Understanding Conference (DUC) evaluations.

Summary in context

The use of text summaries in information-seeking research has focused on query-based summaries. Extracting content that resembles the query alone, however, ignores the greater context of the document. Such context may be central to the purpose and meaning of the document. We developed a generic, a query-based, and a hybrid summarizer, each with differing amounts of document context. The generic summarizer used a blend of discourse information and information obtained through traditional surface-level analysis. The query-based summarizer used only query-term information, and the hybrid summarizer used some discourse information along with query-term information. The validity of the generic summarizer was shown through an intrinsic evaluation using a well-established corpus of human-generated summaries. All three summarizers were then compared in an information-seeking experiment involving 297 subjects. Results from the information-seeking experiment showed that the generic summaries outperformed all others in the browse tasks, while the query-based and hybrid summaries outperformed the generic summary in the search tasks. Thus, the document context of generic summaries helped users browse, while such context was not helpful in search tasks. Such results are interesting given that generic summaries have not been studied in search tasks and the that majority of Internet search engines rely solely on query-based summaries.

Context‐based generic cross‐lingual retrieval of documents and automated summaries

AbstractWe develop a context‐based generic cross‐lingual retrieval model that can deal with different language pairs. Our model considers contexts in the query translation process. Contexts in the query as well as in the documents based on co‐occurrence statistics from different granularity of passages are exploited. We also investigate cross‐lingual retrieval of automatic generic summaries. We have implemented our model for two different cross‐lingual settings, namely, retrieving Chinese documents from English queries as well as retrieving English documents from Chinese queries. Extensive experiments have been conducted on a large‐scale parallel corpus enabling studies on retrieval performance for two different cross‐lingual settings of full‐length documents as well as automated summaries.

SUMMAC: a text summarization evaluation

The TIPSTER Text Summarization Evaluation (SUMMAC) has developed several new extrinsic and intrinsic methods for evaluating summaries. It has established definitively that automatic text summarization is very effective in relevance assessment tasks on news articles. Summaries as short as 17% of full text length sped up decision-making by almost a factor of 2 with no statistically significant degradation in accuracy. Analysis of feedback forms filled in after each decision indicated that the intelligibility of present-day machine-generated summaries is high. Systems that performed most accurately in the production of indicative and informative topic-related summaries used term frequency and co-occurrence statistics, and vocabulary overlap comparisons between text passages. However, in the absence of a topic, these statistical methods do not appear to provide any additional leverage: in the case of generic summaries, the systems were indistinguishable in accuracy. The paper discusses some of the tradeoffs and challenges faced by the evaluation, and also lists some of the lessons learned, impacts, and possible future directions. The evaluation methods used in the SUMMAC evaluation are of interest to both summarization evaluation as well as evaluation of other ‘output-related’ NLP technologies, where there may be many potentially acceptable outputs, with no automatic way to compare them.

Wood and Bark Anatomy of Myricaceae: Relationships, Generic Definitions, and Ecological Interpretations

Wood anatomy of the single species of Canacomyrica (hitherto not studied) shows that it belongs in Myricaceae, although it differs from other genera in several respects (axial parenchyma grouped in bands or columns as well as diffuse; Heterogeneous Type I rays; more numerous bars per perforation plate). The latter two features are primitive for the family. The four genera (Canacomyrica. Comptonia, Morella, and Myrica s.s.) differ from each other not only by qualitative features but by quantitative features (feature means in genera mostly non- overl apping). Wood of Comptonia and Myri ca s.s. lacks chambered crystals in axial parenchyma and ray crystals. Wood of Myrica s.s. has tracheids in latewood but fiber-tracheids in earl ywood. Diagnostic generic summaries are presented. Features of Myricaceae such as scalarifom perforation plates, presence of (true) tracheids , ray types , chambered encapsulated crystals in axial parenchyma, and bark anatomy correspond with character states and expressions in Betulaceae, Casuarinaceae, Corylaceae, Juglandaceae (including Rhoipteleaceae), Ticodendraceae and, to a lesser extent, Fagaceae and Nothofagaceae. This grouping of families can be found as Fagales in recent DNA trees. The predominance of tracheids in basal Fagales such as Myricaceae and Ticodendraceae suggests that origin of vasicentric tracheids which occur in combination with libriform fibers in Fagaceae is the product of tracheid dimorphism. Low imperforate tracheid length to vessel element length ratios (FN ratios) in Myricaceae are a probable indication of wood primitiveness. Quantitative vessel features of Myricaceae, as combined in Mesomorphy Ratio values, characterize wood of Myricaceae as a whole, but at the species level such values correspond to respective habitats; notably high vessel density in Comptonia may represent greater conductive safety appropriate to relatively dry habitats.