Search

Abstract: In this paper, we describe an open information extraction pipeline based on ReVerb for extracting knowledge from French text. We put it to the test by using the information triples extracted to build an entity classifier, ie, a system able to label a given instance with its type (for instance, Michel Foucault is a philosopher). The classifier requires little supervision. One novel aspect of this study is that we show how general domain information triples (extracted from French Wikipedia) can be used for deriving new knowledge from domain‐specific documents unrelated to Wikipedia, in our case scholarly articles focusing on the humanities. We believe that the present study is the first that focuses on such a cross‐domain, recall‐oriented approach in open information extraction. While our system's performance shows room for improvement, manual assessments show that the task is quite hard, even for a human, in part because of the cross‐domain aspect of the problem we tackle. [ABSTRACT FROM AUTHOR]

In this paper we describe the many steps involved in building a production quality Machine Translation system for translating weather warnings between French and English. Although in principle this task may seem straightforward, the details, especially corpus preparation and final text presentation, involve many difficult aspects that are often glossed over in the literature. On top of the classic Statistical Machine Translation evaluation metric results, four manual evaluations have been performed to assess and improve translation quality. We also show the usefulness of the integration of out-of-domain information sources in a Statistical Machine Translation system to produce high quality translated text. [ABSTRACT FROM AUTHOR]

Allergic rhinitis is often associated with bronchial hyperresponsiveness (BHR) and airway inflammation, and it seems to be an important risk factor for the development of asthma. Specific immunotherapy (SIT) reduces symptoms and medication requirements in subjects with allergic rhinitis, but the mechanisms by which SIT promotes these beneficial effects are less clear. We have investigated the effects of Parietaria-SIT on rhinitis symptoms, BHR to inhaled methacholine, eosinophilic inflammation and cytokine production (interferon gamma and interleukin-4) in the sputum. The effect on asthma progression was also examined. Thirty non-asthmatic subjects with seasonal rhinitis and monosensitized to Parietaria judaica participated in a randomized, double-blind, placebo-controlled, parallel group study. Participants were randomly assigned to receive injections of a Parietaria pollen vaccine (n = 15) or matched placebo injections (n = 15) in a rapid updosing cluster regimen for 7 weeks, followed by monthly injections for 34 months. Throughout the 3-year study we collected data on symptoms and medication score, airway responsiveness to methacholine, eosinophilia and soluble cytokines in sputum, followed by a complete evaluation of the clinical course of atopy. Hay fever symptom and medication scores were well controlled by SIT. By the end of the study, in the placebo group, symptom and medication scores significantly increased by a median (interquartile range) of 121% (15-280%) and 263% (0-4400%) respectively (p < 0.01), whereas no significant difference was observed in the SIT group. We found no significant changes in the sputum parameters and methacholine PC15 values in both groups throughout the study. By the end of the investigation, a total of 9 out of 29 participants developed asthma symptoms; of these, seven (47%) belonged to the placebo group, whereas only 2 (14%) to the SIT-treated group (p = 0.056). In conclusion, Parietaria-SIT is effective in controlling hay fever symptoms and rescue medications, but no changes in the BHR to methacholine or sputum eosinophilia were observed. Moreover, Parietaria-SIT appears to prevent the natural progression of allergic rhinitis to asthma, suggesting that SIT should be considered earlier in the management of this condition.