Abstractive summarization is an ideal form of summarization since it can synthesize information from multiple documents to create concise informative summaries. In this work, we aim at developing an abstractive summarizer. First, our proposed approach identifies the most important document in the multi-document set. The sentences in the most important document are aligned to sentences in other documents to generate clusters of similar sentences. Second, we generate K-shortest paths from the sentences in each cluster using a word-graph structure. Finally, we select sentences from the set of shortest paths generated from all the clusters employing a novel integer linear programming (ILP) model with the objective of maximizing information content and readability of the final summary. Our ILP model represents the shortest paths as binary variables and considers the length of the path, information score and linguistic quality score in the objective function. Experimental results on the DUC 2004 and 2005 multi-document summarization datasets show that our proposed approach outperforms all the baselines and state-of-the-art extractive summarizers as measured by the ROUGE scores. Our method also outperforms a recent abstractive summarization technique. In manual evaluation, our approach also achieves promising results on informativeness and readability.
Temporal common sense has applications in AI tasks such as QA, multi-document summarization, and human-AI communication. We propose the task of sequencing -- given a jumbled set of aligned image-caption pairs that belong to a story, the task is to sort them such that the output sequence forms a coherent story. We present multiple approaches, via unary (position) and pairwise (order) predictions, and their ensemble-based combinations, achieving strong results on this task. We use both text-based and image-based features, which depict complementary improvements. Using qualitative examples, we demonstrate that our models have learnt interesting aspects of temporal common sense.
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multi-document summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories.
Due to its promise to alleviate information overload, text summarization has attracted the attention of many researchers. However, it has remained a serious challenge. Here, we first prove empirical limits on the recall (and F1-scores) of extractive summarizers on the DUC datasets under ROUGE evaluation for both the single-document and multi-document summarization tasks. Next we define the concept of compressibility of a document and present a new model of summarization, which generalizes existing models in the literature and integrates several dimensions of the summarization, viz., abstractive versus extractive, single versus multi-document, and syntactic versus semantic. Finally, we examine some new and existing single-document summarization algorithms in a single framework and compare with state of the art summarizers on DUC data.
In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to tackle summary coherence for increasing readability. We conduct experiments on the Document Understanding Conference (DUC) 2004 datasets using ROUGE toolkit. Our experiments demonstrate that the methods bring significant improvements over the state of the art methods in terms of informativity and coherence.
Concept maps can be used to concisely represent important information and bring structure into large document collections. Therefore, we study a variant of multi-document summarization that produces summaries in the form of concept maps. However, suitable evaluation datasets for this task are currently missing. To close this gap, we present a newly created corpus of concept maps that summarize heterogeneous collections of web documents on educational topics. It was created using a novel crowdsourcing approach that allows us to efficiently determine important elements in large document collections. We release the corpus along with a baseline system and proposed evaluation protocol to enable further research on this variant of summarization.
We investigate the problem of reader-aware multi-document summarization (RA-MDS) and introduce a new dataset for this problem. To tackle RA-MDS, we extend a variational auto-encodes (VAEs) based MDS framework by jointly considering news documents and reader comments. To conduct evaluation for summarization performance, we prepare a new dataset. We describe the methods for data collection, aspect annotation, and summary writing as well as scrutinizing by experts. Experimental results show that reader comments can improve the summarization performance, which also demonstrates the usefulness of the proposed dataset. The annotated dataset for RA-MDS is available online.
Due to the large amount of textual information available on Internet, it is of paramount relevance to use techniques that find relevant and concise content. A typical task devoted to the identification of informative sentences in documents is the so called extractive document summarization task. In this paper, we use complex network concepts to devise an extractive Multi Document Summarization (MDS) method, which extracts the most central sentences from several textual sources. In the proposed model, texts are represented as networks, where nodes represent sentences and the edges are established based on the number of shared words. Differently from previous works, the identification of relevant terms is guided by the characterization of nodes via dynamical measurements of complex networks, including symmetry, accessibility and absorption time. The evaluation of the proposed system revealed that excellent results were obtained with particular dynamical measurements, including those based on the exploration of networks via random walks.
We propose a neural multi-document summarization (MDS) system that incorporates sentence relation graphs. We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features. Through multiple layer-wise propagation, the GCN generates high-level hidden sentence features for salience estimation. We then use a greedy heuristic to extract salient sentences while avoiding redundancy. In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining sentence relations in graphs with the representation power of deep neural networks. Our model improves upon traditional graph-based extractive approaches and the vanilla GRU sequence model with no graph, and it achieves competitive results against other state-of-the-art multi-document summarization systems.
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.
Huge volumes of textual information has been produced every single day. In order to organize and understand such large datasets, in recent years, summarization techniques have become popular. These techniques aims at finding relevant, concise and non-redundant content from such a big data. While network methods have been adopted to model texts in some scenarios, a systematic evaluation of multilayer network models in the multi-document summarization task has been limited to a few studies. Here, we evaluate the performance of a multilayer-based method to select the most relevant sentences in the context of an extractive multi document summarization (MDS) task. In the adopted model, nodes represent sentences and edges are created based on the number of shared words between sentences. Differently from previous studies in multi-document summarization, we make a distinction between edges linking sentences from different documents (inter-layer) and those connecting sentences from the same document (intra-layer). As a proof of principle, our results reveal that such a discrimination between intra- and inter-layer in a multilayered representation is able to improve the quality of the generated summaries. This piece of information could be used to improve current statistical methods and related textual models.
We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents. We use extractive summarization to coarsely identify salient information and a neural abstractive model to generate the article. For the abstractive model, we introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. We show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, we show it can extract relevant factual information as reflected in perplexity, ROUGE scores and human evaluations.
Multi-document summarization has received a great deal of attention in the past couple of decades. Several approaches have been proposed, many of which perform equally well and it is becoming in- creasingly difficult to choose one particular system over another. An ensemble of such systems that is able to leverage the strengths of each individual systems can build a better and more robust summary. Despite this, few attempts have been made in this direction. In this paper, we describe a category of ensemble systems which use consensus between the candidate systems to build a better meta-summary. We highlight two major shortcomings of such systems: the inability to take into account relative performance of individual systems and overlooking content of candidate summaries in favour of the sentence rankings. We propose an alternate method, content-based weighted consensus summarization, which address these concerns. We use pseudo-relevant summaries to estimate the performance of individual candidate systems, and then use this information to generate a better aggregate ranking. Experiments on DUC 2003 and DUC 2004 datasets show that the proposed system outperforms existing consensus-based techniques by a large margin.
Till now, neural abstractive summarization methods have achieved great success for single document summarization (SDS). However, due to the lack of large scale multi-document summaries, such methods can be hardly applied to multi-document summarization (MDS). In this paper, we investigate neural abstractive methods for MDS by adapting a state-of-the-art neural abstractive summarization model for SDS. We propose an approach to extend the neural abstractive model trained on large scale SDS data to the MDS task. Our approach only makes use of a small number of multi-document summaries for fine tuning. Experimental results on two benchmark DUC datasets demonstrate that our approach can outperform a variety of baseline neural models.
We report a series of experiments with different semantic models on top of various statistical models for extractive text summarization. Though statistical models may better capture word co-occurrences and distribution around the text, they fail to detect the context and the sense of sentences /words as a whole. Semantic models help us gain better insight into the context of sentences. We show that how tuning weights between different models can help us achieve significant results on various benchmarks. Learning pre-trained vectors used in semantic models further, on given corpus, can give addition spike in performance. Using weighing techniques in between different statistical models too further refines our result. For Statistical models, we have used TF/IDF, TextRAnk, Jaccard/Cosine Similarities. For Semantic Models, we have used WordNet-based Model and proposed two models based on Glove Vectors and Facebook's InferSent. We tested our approach on DUC 2004 dataset, generating 100-word summaries. We have discussed the system, algorithms, analysis and also proposed and tested possible improvements. ROUGE scores were used to compare to other summarizers.
As the number of documents on the web is growing exponentially, multi-document summarization is becoming more and more important since it can provide the main ideas in a document set in short time. In this paper, we present an unsupervised centroid-based document-level reconstruction framework using distributed bag of words model. Specifically, our approach selects summary sentences in order to minimize the reconstruction error between the summary and the documents. We apply sentence selection and beam search, to further improve the performance of our model. Experimental results on two different datasets show significant performance gains compared with the state-of-the-art baselines.
Generating an abstract from a collection of documents is a desirable capability for many real-world applications. However, abstractive approaches to multi-document summarization have not been thoroughly investigated. This paper studies the feasibility of using Abstract Meaning Representation (AMR), a semantic representation of natural language grounded in linguistic theory, as a form of content representation. Our approach condenses source documents to a set of summary graphs following the AMR formalism. The summary graphs are then transformed to a set of summary sentences in a surface realization step. The framework is fully data-driven and flexible. Each component can be optimized independently using small-scale, in-domain training data. We perform experiments on benchmark summarization datasets and report promising results. We also describe opportunities and challenges for advancing this line of research.