Learn More
In this work, we study the problem of measuring relational similarity between two word pairs (e.g., silverware:fork and clothing:shirt). Due to the large number of possible relations, we argue that it is important to combine multiple models based on heterogeneous information sources. Our overall system consists of two novel general-purpose relational(More)
The information obtained from the Web is increasingly important for decision making and for our everyday tasks. Due to the growth of uncertified sources, blogosphere, comments in the social media and automatically generated texts, the need to measure the quality of text information found on the Internet is becoming of crucial importance. It has been(More)
Visual evoked potentials in response to images of a set of horizontal and vertical lines or crosses were recorded from the brains of 18 human subjects in 34 leads. Inverse EEG analyses were used for the dynamic location of the dipole current sources of the N1, P1, and N2 waves using a two-dipole spherical model with a 1-msec step. The occipital lobes of all(More)
Open Information Extraction (Open IE) serves for the analysis of vast amounts of texts by extraction of assertions, or relations , in the form of tuples argument 1; relation; argument 2. Various approaches to Open IE have been designed to perform in a fast, unsupervised manner. All of them require language specific information for their implementation. In(More)
Usually we do not know the domain of an arbitrary text from the Internet, or the semantics of the relations it conveys. While humans identify such information easily, for a computer this task is far from straightforward. The task of detecting relations of arbitrary semantic type in texts is known as Open Information Extraction (Open IE). The approach to(More)
In 2010's several exabytes of data are produced daily. Approximately between 1 ⁄5 and 1 ⁄3 of these data is text. To make use of such huge amounts of textual data, we need to be able to detect, to extract, to structure, and to process important information conveyed through this data flow in a fast and scalable manner. Open information extraction (Open IE)(More)
Dynamic study of 3D localization of the equivalent current dipole (ECD) sources of visual evoked potentials (EP) in the human brain was performed in 18 healthy subjects using a two-dipole model. Dipole tracing was performed for relatively early EP components (N1, P1, and N2) with 1-ms step. The analysis confirmed localization of these ECDs mainly in the(More)
Broadly defined my area of research is computational linguistics and natural language processing. More specifically, my main research interest lies in open information extraction from text and its applications to text quality evaluation, in particular, text informativeness. Departing from these areas, I have also worked on the problems of human opinion(More)
  • 1