Using a recent convex formulation of IBM Model 2, we propose a new initialization scheme which has some favorable comparisons to the standard method of initializing IBM Model 2 with IBM Model 1. Additionally, we derive the Viterbi alignment for the convex relaxation of IBM Model 2 and show that it leads to better F-Measure scores than those of IBM Model 2.

Mixture modelling is a standard pattern classification technique. However, in statistical machine translation, the use of mixture modelling is still unexplored. Two main advantages of the mixture approach are first, its flexibility to find an appropriate tradeoff between model complexity and the amount of training data available and second, its capability to learn specific probability distribut...

RuleBase is a symbolic model checking tool, developed by the IBM Haifa Research Laboratory. It is the result of four years of experience in practical formal verification of hardware which, we believe, has been a key factor in bringing the tool to its current level of maturity. Our experience shows that after a short training period, designers can operate the tool independently and achieve impre...

In this paper, we describe the system jointly developed by IBM Research and Columbia University for video copy detection and multimedia event detection applied to the TRECVID-2010 video retrieval benchmark. A. Content-Based Copy Detection: The focus of our copy detection system this year was fusing three types of complementary fingerprints: a keyframe-based color correlogram, SIFTogram (bag of ...

In this paper, we attempt to generalize the ideal binary mask (IBM) estimation to the ideal ratio mask (IRM) estimation. Under binary masking, the error in IBM estimation may greatly distort the original speech spectrum. The main purpose of this paper is using ratio mask to smooth this negative impact. Since the key issue is the noise tracking, we firstly use exponential distributions to model ...

In this paper, we present a Bayesian Learning based method to train word dependent transition models for HMM based word alignment. We present word alignment results on the Canadian Hansards corpus as compared to the conventional HMM and IBM model 4. We show that this method gives consistent and significant alignment error rate (AER) reduction. We also conducted machine translation (MT) experime...

In this paper, we explore the IBM Model with a `0-norm prior to the semantic parsing which parses a sentence to its corresponding meaning representation, and compare two supervised probabilistic Combinatory Categorial Grammar (PCCG) online learning approaches that are Unification-Based Learning (UBL) method and Factored Unification-Based Learning (FUBL) one. Specially, we extend manually GeoQue...

I consider mathematical modelling and simulation to be both a legitimate intellectual exercise, and a practical aid to policy analysis and decision-making. However to the extent that there is an issue revolving around understanding models versus understanding systems, then I am fully committed to the systems camp. I think it is a cop out to produce models which may exhibit all kinds of interest...

Most statistical translation systems are based on phrase translation pairs, or “blocks”, which are obtained mainly from word alignment. We use blocks to infer better word alignment and improved word alignment which, in turn, leads to better inference of blocks. We propose two new probabilistic models based on the innerouter segmentations and use EM algorithms for estimating the models’ paramete...