Word frequency-based methods for extractive summarization are easy to implement and yield reasonable results across languages. However, they have significant limitations - they ignore the role of context, they offer uneven coverage of topics in a document, and sometimes are disjointed and hard to read. We use a simple premise from linguistic typology - that English sentences are complete descriptors of potential interactions between entities, usually in the order subject-verb-object - to address a subset of these difficulties. We have developed a hybrid model of extractive summarization that combines word-frequency based keyword identification with information from automatically generated entity relationship graphs to select sentences for summaries. Comparative evaluation with word-frequency and topic word-based methods shows that the proposed method is competitive by conventional ROUGE standards, and yields moderately more informative summaries on average, as assessed by a large panel (N=94) of human raters.
Automatic text summarization is generally considered as a challenging task in the NLP community. One of the challenges is the publicly available and large dataset that is relatively rare and difficult to construct. The problem is even worse for low-resource languages such as Indonesian. In this paper, we present IndoSum, a new benchmark dataset for Indonesian text summarization. The dataset consists of news articles and manually constructed summaries. Notably, the dataset is almost 200x larger than the previous Indonesian summarization dataset of the same domain. We evaluated various extractive summarization approaches and obtained encouraging results which demonstrate the usefulness of the dataset and provide baselines for future research. The code and the dataset are available online under permissive licenses.
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstrating that BanditSum is able to achieve ROUGE scores that are better than or comparable to the state-of-the-art for extractive summarization, and converges using significantly fewer update steps than competing approaches. In addition, we show empirically that BanditSum performs significantly better than competing approaches when good summary sentences appear late in the source document.
With an ever growing number of extractive summarization techniques being proposed, there is less clarity then ever about how good each system is compared to the rest. Several studies highlight the variance in performance of these systems with change in datasets or even across documents within the same corpus. An effective way to counter this variance and to make the systems more robust could be to use inputs from multiple systems when generating a summary. In the present work, we define a novel way of creating such ensemble by exploiting similarity between the content of candidate summaries to estimate their reliability. We define GlobalRank which captures the performance of a candidate system on an overall corpus and LocalRank which estimates its performance on a given document cluster. We then use these two scores to assign a weight to each individual systems, which is then used to generate the new aggregate ranking. Experiments on DUC2003 and DUC 2004 datasets show a significant improvement in terms of ROUGE score, over existing sate-of-art techniques.
Extractive summarization models require sentence-level labels, which are usually created heuristically (e.g., with rule-based methods) given that most summarization datasets only have document-summary pairs. Since these labels might be suboptimal, we propose a latent variable extractive model where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries. During training the loss comes \emph{directly} from gold summaries. Experiments on the CNN/Dailymail dataset show that our model improves over a strong extractive baseline trained on heuristically approximated labels and also performs competitively to several recent models.
Sequence to sequence (Seq2Seq) learning has recently been used for abstractive and extractive summarization. In current study, Seq2Seq models have been used for eBay product description summarization. We propose a novel Document-Context based Seq2Seq models using RNNs for abstractive and extractive summarizations. Intuitively, this is similar to humans reading the title, abstract or any other contextual information before reading the document. This gives humans a high-level idea of what the document is about. We use this idea and propose that Seq2Seq models should be started with contextual information at the first time-step of the input to obtain better summaries. In this manner, the output summaries are more document centric, than being generic, overcoming one of the major hurdles of using generative models. We generate document-context from user-behavior and seller provided information. We train and evaluate our models on human-extracted-golden-summaries. The document-contextual Seq2Seq models outperform standard Seq2Seq models. Moreover, generating human extracted summaries is prohibitively expensive to scale, we therefore propose a semi-supervised technique for extracting approximate summaries and using it for training Seq2Seq models at scale. Semi-supervised models are evaluated against human extracted summaries and are found to be of similar efficacy. We provide side by side comparison for abstractive and extractive summarizers (contextual and non-contextual) on same evaluation dataset. Overall, we provide methodologies to use and evaluate the proposed techniques for large document summarization. Furthermore, we found these techniques to be highly effective, which is not the case with existing techniques.
Sentence scoring and sentence selection are two main steps in extractive document summarization systems. However, previous works treat them as two separated subtasks. In this paper, we present a novel end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences. It first reads the document sentences with a hierarchical encoder to obtain the representation of sentences. Then it builds the output summary by extracting sentences one by one. Different from previous methods, our approach integrates the selection strategy into the scoring model, which directly predicts the relative importance given previously selected sentences. Experiments on the CNN/Daily Mail dataset show that the proposed framework significantly outperforms the state-of-the-art extractive summarization models.
We explore methods for content selection and address the issue of coherence in the context of the generation of multimedia artifacts. We use audio and video to present two case studies: generation of film tributes, and lecture-driven science talks. For content selection, we use centrality-based and diversity-based summarization, along with topic analysis. To establish coherence, we use the emotional content of music, for film tributes, and ensure topic similarity between lectures and documentaries, for science talks. Composition techniques for the production of multimedia artifacts are addressed as a means of organizing content, in order to improve coherence. We discuss our results considering the above aspects.
Extractive summarization aims at selecting a set of indicative sentences from a source document as a summary that can express the major theme of the document. A general consensus on extractive summarization is that both relevance and coverage are critical issues to address. The existing methods designed to model coverage can be characterized by either reducing redundancy or increasing diversity in the summary. Maximal margin relevance (MMR) is a widely-cited method since it takes both relevance and redundancy into account when generating a summary for a given document. In addition to MMR, there is only a dearth of research concentrating on reducing redundancy or increasing diversity for the spoken document summarization task, as far as we are aware. Motivated by these observations, two major contributions are presented in this paper. First, in contrast to MMR, which considers coverage by reducing redundancy, we propose two novel coverage-based methods, which directly increase diversity. With the proposed methods, a set of representative sentences, which not only are relevant to the given document but also cover most of the important sub-themes of the document, can be selected automatically. Second, we make a step forward to plug in several document/sentence representation methods into the proposed framework to further enhance the summarization performance. A series of empirical evaluations demonstrate the effectiveness of our proposed methods.
We study the problem of generating abstractive summaries for opinionated text. We propose an attention-based neural network model that is able to absorb information from multiple text units to construct informative, concise, and fluent summaries. An importance-based sampling method is designed to allow the encoder to integrate information from an important subset of input. Automatic evaluation indicates that our system outperforms state-of-the-art abstractive and extractive summarization systems on two newly collected datasets of movie reviews and arguments. Our system summaries are also rated as more informative and grammatical in human evaluation.
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction. We adapt an existing in-domain relation learner (Chen et al., 2011) by exploiting a set of task-specific constraints and features. We evaluate the approach on a decision summarization task and show that it outperforms unsupervised utterance-level extractive summarization baselines as well as an existing generic relation-extraction-based summarization method. Moreover, our approach produces summaries competitive with those generated by supervised methods in terms of the standard ROUGE score.
Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summarization datasets demonstrate that our models obtain results comparable to the state of the art without any access to linguistic annotation.
Concepts and methods of complex networks can be used to analyse texts at their different complexity levels. Examples of natural language processing (NLP) tasks studied via topological analysis of networks are keyword identification, automatic extractive summarization and authorship attribution. Even though a myriad of network measurements have been applied to study the authorship attribution problem, the use of motifs for text analysis has been restricted to a few works. The goal of this paper is to apply the concept of motifs, recurrent interconnection patterns, in the authorship attribution task. The absolute frequencies of all thirteen directed motifs with three nodes were extracted from the co-occurrence networks and used as classification features. The effectiveness of these features was verified with four machine learning methods. The results show that motifs are able to distinguish the writing style of different authors. In our best scenario, 57.5% of the books were correctly classified. The chance baseline for this problem is 12.5%. In addition, we have found that function words play an important role in these recurrent patterns. Taken together, our findings suggest that motifs should be further explored in other related linguistic tasks.
We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejects each sentence in the original document order for its membership in the final summary. The Selector architecture, on the other hand, is free to pick one sentence at a time in any arbitrary order to piece together the summary. Our models under both architectures jointly capture the notions of salience and redundancy of sentences. In addition, these models have the advantage of being very interpretable, since they allow visualization of their predictions broken up by abstract features such as information content, salience and redundancy. We show that our models reach or outperform state-of-the-art supervised models on two different corpora. We also recommend the conditions under which one architecture is superior to the other based on experimental evidence.
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional advantage of being very interpretable, since it allows visualization of its predictions broken up by abstract features such as information content, salience and novelty. Another novel contribution of our work is abstractive training of our extractive model that can train on human generated reference summaries alone, eliminating the need for sentence-level extractive labels.
To analyze the limitations and the future directions of the extractive summarization paradigm, this paper proposes an Integer Linear Programming (ILP) formulation to obtain extractive oracle summaries in terms of ROUGE-N. We also propose an algorithm that enumerates all of the oracle summaries for a set of reference summaries to exploit F-measures that evaluate which system summaries contain how many sentences that are extracted as an oracle summary. Our experimental results obtained from Document Understanding Conference (DUC) corpora demonstrated the following: (1) room still exists to improve the performance of extractive summarization; (2) the F-measures derived from the enumerated oracle summaries have significantly stronger correlations with human judgment than those derived from single oracle summaries.
In this work, we present a compact, modular framework for constructing novel recurrent neural architectures. Our basic module is a new generic unit, the Transition Based Recurrent Unit (TBRU). In addition to hidden layer activations, TBRUs have discrete state dynamics that allow network connections to be built dynamically as a function of intermediate activations. By connecting multiple TBRUs, we can extend and combine commonly used architectures such as sequence-to-sequence, attention mechanisms, and re-cursive tree-structured models. A TBRU can also serve as both an encoder for downstream tasks and as a decoder for its own task simultaneously, resulting in more accurate multi-task learning. We call our approach Dynamic Recurrent Acyclic Graphical Neural Networks, or DRAGNN. We show that DRAGNN is significantly more accurate and efficient than seq2seq with attention for syntactic dependency parsing and yields more accurate multi-task learning for extractive summarization tasks.
This paper addresses automatic summarization and search in visual data comprising of videos, live streams and image collections in a unified manner. In particular, we propose a framework for multi-faceted summarization which extracts key-frames (image summaries), skims (video summaries) and entity summaries (summarization at the level of entities like objects, scenes, humans and faces in the video). The user can either view these as extractive summarization, or query focused summarization. Our approach first pre-processes the video or image collection once, to extract all important visual features, following which we provide an interactive mechanism to the user to summarize the video based on their choice. We investigate several diversity, coverage and representation models for all these problems, and argue the utility of these different mod- els depending on the application. While most of the prior work on submodular summarization approaches has focused on combining several models and learning weighted mixtures, we focus on the explain-ability of different the diversity, coverage and representation models and their scalability. Most importantly, we also show that we can summarize hours of video data in a few seconds, and our system allows the user to generate summaries of various lengths and types interactively on the fly.
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.
Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights those points that are relevant in the context of a given query. The encode-attend-decode paradigm has achieved notable success in machine translation, extractive summarization, dialog systems, etc. But it suffers from the drawback of generation of repeated phrases. In this work we propose a model for the query-based summarization task based on the encode-attend-decode paradigm with two key additions (i) a query attention model (in addition to document attention model) which learns to focus on different portions of the query at different time steps (instead of using a static representation for the query) and (ii) a new diversity based attention model which aims to alleviate the problem of repeating phrases in the summary. In order to enable the testing of this model we introduce a new query-based summarization dataset building on debatepedia. Our experiments show that with these two additions the proposed model clearly outperforms vanilla encode-attend-decode models with a gain of 28% (absolute) in ROUGE-L scores.