Abhishek Arun

Learn More
This paper presents the first probabilistic parsing results for French, using the recently released French Treebank. We start with an unlexicalized PCFG as a baseline model, which is enriched to the level of Collins’ Model 2 by adding lexicalization and subcategorization. The lexicalized sister-head model and a bigram model are also tested, to deal with the(More)
This paper investigates the task of training discriminatively a phrase based SMT system with millions of features using the structured perceptron and the Margin Infused Relax Algorithm (MIRA), two popular online learning algorithms. We also compare two different update strategies, one where we update towards an oracle translation candidate extracted from an(More)
Recent advances in statistical machine translation have used beam search for approximate NP-complete inference within probabilistic translation models. We present an alternative approach of sampling from the posterior distribution defined by a translation model. We define a novel Gibbs sampler for sampling translations given a source sentence and show that(More)
Statistical machine translation systems are normally optimised for a chosen gain function (metric) by using MERT to find the best model weights. This algorithm suffers from stability problems and cannot scale beyond 20-30 features. We present an alternative algorithm for discriminative training of phrasebasedMT systems, SampleRank, which scales to hundreds(More)
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative approach of sampling from the posterior distribution defined by a translation model. We define a novel Gibbs sampler for sampling translations given a source sentence and show that(More)
In this paper we describe the Edinburgh University statistical machine translation system, as used for the TC-STAR 2006 evaluation campaign. We participated in the primary Final Text Edition track for the Spanish to English and English to Spanish translation tasks, using only the provided datasets for training our translation and language models. We(More)
We present an unconventional but high performance pulsating conductivity monitoring instrument constructed by using a new class of sensor, viz., pulsating sensor developed in house. The design consists of a special type of logic gate oscillator (LGO) powered by 5 V direct current (dc). The conductivity cell constitutes a part of LGO. In this conductivity(More)
A novel approach towards deployment of a hydrostatic pressure based level monitoring device is presented for continuous monitoring of liquid level in a reservoir with high resolution and precision. Some of the major drawbacks such as spurious information of measured level due to change in ambient temperature, requirement of high resolution pressure sensor,(More)