This work deals with determination of meaningful and terse cluster labels for News document clusters. We analyze a number of alternatives for selecting headlines and/or sentences of document in a document cluster (obtained as a result of an entity-event-duration query), and formalize an approach to extracting a short phrase from well-supported headlines/sentences of the cluster that can serve a...

Rhetorical figures appear frequently in the headlines of magazine ads. This paper examines the effect of repetition on ads containing two types of rhetorical figures: easyto-understand rhymes and challenging puns. The findings indicate that high levels of repetition may not be necessary when ad headlines contain such rhetorical figures, even under conditions where subjects are not directed to p...

Do the discoveries of cognitive science generalize beyond artificial lab experiments? Or do they have little hope of helping us to understand real-world events? Fretting on this question, I bought a copy of the Wall Street Journal and found that the three front page headlines each connect to my own research on explanatory reasoning. I report tests of the phenomena of inferred evidence, belief d...

News headlines are a vital source of information for the masses. Identifying diseases that are being spread or discovered is important to take necessary steps for their prevention and cure. Our system uses a syntactic and lexical constraint-based approach which then goes through a frequency analysis phase to extract meaningful disease names. In the task of top-150 (unique) disease mention recog...

This research aimed to measure the effectiveness of Thai news headlines classification using an artificial neural network (ANN). The consisted i) political news, ii) sports iii) economic and iv) crime 1,200 in total. distribution was measured by chi-square, information gain, term frequency inverse class (TFICF). Threshold default value set relation terms before cross-validation employed categor...

We describe our efforts to generate a large (100,000 instance) corpus of textual entailment pairs from the lead paragraph and headline of news articles. We manually inspected a small set of news stories in order to locate the most productive source of entailments, then built an annotation interface for rapid manual evaluation of further exemplars. With this training data we built an SVM-based d...

The current study focuses on the similarities and differences of conceptual metaphor and metonymy between each genre in newspaper headlines. Headlines in news articles in Apple Daily from May 21 to May 27 were collected and analyzed. There are three basic findings. First, blocks for entertainment and sports used, in proportion, more metaphors and metonymies than any other blocks. Second, the id...

Data sources like the clusters of news headlines at Google News present an exciting opportunity to learn paraphrase models from data automatically. We present both a novel dataset and a novel approach to automatic, unsupervised learning of paraphrase models from that datset. Leveraging existing NLP tools such as the Stanford Parser and lexical resources such as WordNet and Infomap, we construct...