The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Question answering (QA) is an important research issue in natural language processing, and most state-of the-art question answering systems are based on statistical models. After witnessing recent achievements in Artificial Intelligent (AI), many businesses wish to apply those techniques to an automatic QA system that is capable of providing 24-hour customer services for their clients. However, one...
Very high mobility of 149∼189 cm2/Vs, large on-to-off current ratio (ION/IOff) of >7 orders of magnitude, fast turn-on sub-threshold swing of 110 mV/decade, and low power operation at 2∼2.5 V were achieved in SnO2 TFT device at an ultra-thin SnO2 thickness of 4.5 nm. The device mobility of SnO2 TFT is higher than the best ZnO-based TFTs and CVD-grown multi-layers MoS2 MOSFETs. The reached mobility...
In this study, we offer some suggestions for the curriculum content design in teaching Mandarin Chinese as a second language based on our experimental works, with the aid of computational linguistics.
We present a framework for identifying the most representative sentence patterns from semantically and syntactically-annotated corpora via a Semantic Frame Generation (SFG). One of the difficulties to find out similar concepts from a text is because of the variations in linguistic expressions. SFG uses linguistic units as backbones to generate the most prominent patterns from various Chinese DE phrases.
In this paper, a novel Chinese word similarity measuring algorithm is proposed. It utilizes the information in Chinese dictionaries and decomposition of all the word definition in E-HowNet into semantic attributes which include hidden relationships and meanings. The extracted semantic attributes are regarded as semantic vectors for word similarity measurement. Evaluation results not only show that...
Textual Entailment (TE) is the task of recognizing entailment, paraphrase, and contradiction relations between a given text pair. The goal of textual entailment research is to develop a core inference component that can be applied to various domains such as QA. We observed several rank correlations on the data and system results in the NTCIR-10 RITE-2 task, trying to find out correlations between...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.