We present the results of a large-scale, end-to-end human evaluation of various sentiment summarization models. The evaluation shows that users have a strong preference for summarizers that model sentiment over non-sentiment baselines, but have no broad overall preference between any of the sentiment-based models. However, an analysis of the human judgments suggests that there are identifiable ...

With the progress in machine translation, it becomes more subtle to develop the evaluation metric capturing the systems’ differences in comparison to the human translations. In contrast to the current efforts in leveraging more linguistic information to depict translation quality, this paper takes the thread of combining language independent features for a robust solution to MT evaluation metri...

Recently a few systems for automatically solving math word problems have reported promising results. However, the datasets used for evaluation have limitations in both scale and diversity. In this paper, we build a large-scale dataset which is more than 9 times the size of previous ones, and contains many more problem types. Problems in the dataset are semiautomatically obtained from community ...

With the growth of different search engines, it becomes difficult for an user to search particular information effectively. If a search engine could provide domain specific information such as that confines only to a particular topicality, it is referred to as domain specific engine. Applying the ranking model trained for broad-based search to a domain specific search does not achieve good perf...

Route instructions for pedestrians are usually better understood if they include references to landmarks, andmoreover, these landmarks should be as salient as possible. In this paper, we present an approach for automatically deriving a mathematical model of salience directly from route instructions given by humans. Each possible landmark that a person can refer to in a given situation is modell...

In this paper, we present Farasa, a fast and accurate Arabic segmenter. Our approach is based on SVM-rank using linear kernels. We measure the performance of the segmenter in terms of accuracy and efficiency, in two NLP tasks, namely Machine Translation (MT) and Information Retrieval (IR). Farasa outperforms or is at par with the stateof-the-art Arabic segmenters (Stanford and MADAMIRA), while ...

Air quality prediction is highly important in view of the health impacts caused by exposure to air pollutants in urban air. This work has presented a model based on support vector machine (SVM) technique to predict daily average carbon monoxide (CO) concentrations in the atmosphere of Tehran. Two types of SVM regression models, i.e. -SVM and -SVM techniques, were used to predict average daily C...