M. Rotaru

Learn More
We are applying a memory based learning (MBL) algorithm to the task of automatic dialog act (DA) tagging. This work is along the lines of a recent trend that considers MBL as being more appropriate for natural language processing. We did the experiments on the Switchboard corpus, overcome the problem of feature selection and yield results that seem to be(More)
This paper presents a strategy for testing future generations of wafer-level packaged logic devices that have nanoscale I/O structures. The strategy assumes that the devices incorporate built-in self test (BIST) features so that only a subset of the functional I/O needs to be directly accessed during testing. A miniature tester is described that provides(More)
A measurement of the inclusive deep inelastic neutral current e + p scattering cross section is reported in the region of four-momentum transfer squared, 12 GeV 2 ≤ Q 2 ≤ 150 GeV 2 , and Bjorken x, 2 · 10 −4 ≤ x ≤ 0.1. The results are based on data collected by the H1 Collaboration at the ep collider HERA at positron and proton beam energies of E e = 27.6(More)
A search for second and third generation scalar and vector leptoquarks produced in ep collisions via the lepton flavour violating processes ep → µX and ep → τ X is performed by the H1 experiment at HERA. The full data sample taken at a centre-of-mass energy √ s = 319 GeV is used for the analysis, corresponding to an integrated luminosity of 245 pb −1 of e +(More)
The cross section of diffractive deep-inelastic scattering ep → eXp is measured, where the system X contains at least two jets and the leading final state proton is detected in the H1 Forward Proton Spectrometer. The measurement is performed for fractional proton longitudinal momentum loss x IP < 0.1 and covers the range 0.1 < |t| < 0.7 GeV 2 in squared(More)
Many practical information extraction systems use simple taxonomies for mapping extracted strings to client-specific concept codes. In such taxonomies, concepts are defined as groups of semantically similar words and phrases. For the mapping to be accurate, a new client-specific taxonomy – usually nothing more than a set of concept codes, each with a single(More)
This paper presents a deep architecture for learning a similarity metric on variable-length character sequences. The model combines a stack of character-level bidi-rectional LSTM's with a Siamese architecture. It learns to project variable-length strings into a fixed-dimensional embedding space by using only information about the similarity between pairs of(More)
The cross section of the diffractive process e + p → e + Xp is measured at a centre-of-mass energy of 318 GeV, where the system X contains at least two jets and the leading final state proton p is detected in the H1 Very Forward Proton Spectrometer. The measurement is performed in photoproduction with photon virtualities Q 2 < 2 GeV 2 and in deep-inelastic(More)