We demonstrate TextRank – a system for unsupervised extractive summarization that relies on the application of iterative graphbased ranking algorithms to graphs encoding the cohesive structure of a text. An important characteristic of the system is that it does not rely on any language-specific knowledge resources or any manually constructed training data, and thus it is highly portable to new ...

Most approaches to extractive summarization define a set of features upon which selection of sentences is based, using algorithms independent of the features themselves. We propose a new set of features based on low-level, atomic events that describe relationships between important actors in a document or set of documents. We investigate the effect this new feature has on extractive summarizati...

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 pie...

The macroscopical characters of the leaves, leaf constants, physico-chemical constants, extractive values, colour, consistency, pH, extractive values with different solvents, micro chemical test, fluorescence characters of liquid extracts and leaf powder after treatment with different chemical reagents under visible and UV light at 254mn, measurement of cell and tissues were studied to fix some...

We present a new method to generate extractive multi-document summaries. The method uses Integer Linear Programming to jointly maximize the importance of the sentences it includes in the summary and their diversity, without exceeding a maximum allowed summary length. To obtain an importance score for each sentence, it uses a Support Vector Regression model trained on human-authored summaries, w...

Extractive summarization is the strategy of concatenating extracts taken from a corpus into a summary, while abstractive summarization involves paraphrasing the corpus using novel sentences. We define a novel measure of corpus controversiality of opinions contained in evaluative text, and report the results of a user study comparing extractive and NLG-based abstractive summarization at differen...

Sentence compression has attracted much interest in recent years, but most sentence compressors are extractive, i.e., they only delete words. There is a lack of appropriate datasets to train and evaluate abstractive sentence compressors, i.e., methods that apart from deleting words can also rephrase expressions. We present a new dataset that contains candidate extractive and abstractive compres...

In this paper we address two key challenges for extractive multi-document summarization: the search problem of finding the best scoring summary and the training problem of learning the best model parameters. We propose an A* search algorithm to find the best extractive summary up to a given length, which is both optimal and efficient to run. Further, we propose a discriminative training algorit...

Supervised methods for extractive speech summarization require a large training set. Summary annotation is often expensive and time consuming. In this paper, we exploit semi-supervised approaches to leverage unlabeled data. In particular, we investigate co-training for the task of extractive meeting summarization. Compared with text summarization, speech summarization task has its unique charac...