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...

Since many existing systems have been still working even these system have several problems in extending or maintaining. This is big obstacle for company to adopt the product line engineering. Extractive approach can be alternative approach when the company has their own system and adopt product line engineering. In extractive approach, commonality and variability modeling is critical also. In ...

In this paper we tackle the problem of automatic caption generation for news images. Our approach leverages the vast resource of pictures available on the web and the fact that many of them are captioned. Inspired by recent work in summarization, we propose extractive and abstractive caption generation models. They both operate over the output of a probabilistic image annotation model that prep...

Free and esterified sitosterol, the main lipophilic constituents of eucalypt wood extractives, have been associated with the formation of pitch deposits during manufacturing of environmentally-sound paper pulp from Eucalyptus globulus wood. These, and other lipophilic compounds, were analyzed by gas chromatography-mass spectrometry in the course of wood treatments (up to 7 weeks) with four extr...

Single document summarization is the task of producing a shorter version of a document while preserving its principal information content. In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective. We use our algorithm to train a neural ...

The influence of extractive content on the thermal stability and kinetic degradation of two wood species has been investigated using chemical analysis and thermogravimetry. Two wood species were studied: Pinus taeda and Eucalyptus grandis. Thermogravimetric results showed that higher extractive contents in the wood accelerate the degradation process and promote an increase in the conversion val...

In this research, we propose the task of question summarization. We first analyzed question-summary pairs extracted from a Community Question Answering (CQA) site, and found that a proportion of questions cannot be summarized by extractive approaches but requires abstractive approaches. We created a dataset by regarding the question-title pairs posted on the CQA site as question-summary pairs. ...

We present a dual decomposition framework for multi-document summarization, using a model that jointly extracts and compresses sentences. Compared with previous work based on integer linear programming, our approach does not require external solvers, is significantly faster, and is modular in the three qualities a summary should have: conciseness, informativeness, and grammaticality. In additio...