We present a simple and scalable algorithm for maximum-margin estimation of structured output models, including an important class of Markov networks and combinatorial models. We formulate the estimation problem as a convex-concave saddle-point problem that allows us to use simple projection methods based on the dual extragradient algorithm (Nesterov, 2003). The projection step can be solved using dynamic programming or combinatorial algorithms for min-cost convex flow, depending on the structure of the problem. We show that this approach provides a memory-efficient alternative to formulations based on reductions to a quadratic program (QP). We analyze the convergence of the method and present experiments on two very different structured prediction tasks: 3D image segmentation and word alignment, illustrating the favorable scaling properties of our algorithm. 1 1.

As a fundamental problem in pattern recognition, graph matching has found a variety of applications in the field of computer vision. In graph matching, patterns are modeled as graphs and pattern recognition amounts to finding a correspondence between the nodes of different graphs. There are many ways in which the problem has been formulated, but most can be cast in general as a quadratic assignment problem, where a linear term in the objective function encodes node compatibility functions and a quadratic term encodes edge compatibility functions. The main research focus in this theme is about designing efficient algorithms for solving approximately the quadratic assignment problem, since it is NP-hard. In this paper, we turn our attention to the complementary problem: how to estimate compatibility functions such that the solution of the resulting graph matching problem best matches the expected solution that a human would manually provide. We present a method for learning graph matching: the training examples are pairs of graphs and the “labels” are matchings between pairs of graphs. We present experimental results with real image data which give evidence that learning can improve the performance of standard graph matching algorithms. In particular, it turns out that linear assignment with such a learning scheme may improve over state-of-the-art quadratic assignment relaxations. This finding suggests that for a range of problems where quadratic assignment was thought to be essential for securing good results, linear assignment, which is far more efficient, could be just sufficient if learning is performed. This enables speed-ups of graph matching by up to 4 orders of magnitude while retaining state-of-the-art accuracy. 1.

For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative models could be used to enhance or replace the standard generative approach. Building on this work, we demonstrate substantial improvement in word-alignment accuracy, partly though improved training methods, but predominantly through selection of more and better features. Our best model produces the lowest alignment error rate yet reported on Canadian Hansards bilingual data. 1

This paper addresses the task of aligning a database with a corresponding text. The goal is to link individual database entries with sentences that verbalize the same information. By providing explicit semantics-to-text links, these alignments can aid the training of natural language generation and information extraction systems. Beyond these pragmatic benefits, the alignment problem is appealing from a modeling perspective: the mappings between database entries and text sentences exhibit rich structural dependencies, unique to this task. Thus, the key challenge is to make use of as many global dependencies as possible without sacrificing tractability. To this end, we cast text-database alignment as a structured multilabel classification task where each sentence is labeled with a subset of matching database entries. In contrast to existing multilabel classifiers, our approach operates over arbitrary global features of inputs and proposed labels. We compare our model with a baseline classifier that makes locally optimal decisions. Our results show that the proposed model yields a 15% relative reduction in error, and compares favorably with human performance. 1

Abstract not found

In this paper a new discriminative word alignment method is presented. This approach models directly the alignment matrix by a conditional random field (CRF) and so no restrictions to the alignments have to be made. Furthermore, it is easy to add features and so all available information can be used. Since the structure of the CRFs can get complex, the inference can only be done approximately and the standard algorithms had to be adapted. In addition, different methods to train the model have been developed. Using this approach the alignment quality could be improved by up to 23 percent for 3 different language pairs compared to a combination of both IBM4alignments. Furthermore the word alignment was used to generate new phrase tables. These could improve the translation quality significantly. 1

Word alignment is the problem of annotating parallel text with translational correspondence. Previous generative word alignment models have made structural assumptions such as the 1-to-1, 1-to-N, or phrase-based consecutive word assumptions, while previous discriminative models have either made such an assumption directly or used features derived from a generative model making one of these assumptions. We present a new generative alignment model which avoids these structural limitations, and show that it is effective when trained using both unsupervised and semi-supervised training methods. 1

We develop a new objective function for word alignment that measures the size of the bilingual dictionary induced by an alignment. A word alignment that results in a small dictionary is preferred over one that results in a large dictionary. In order to search for the alignment that minimizes this objective, we cast the problem as an integer linear program. We then extend our objective function to align corpora at the sub-word level, which we demonstrate on a small Turkish-English corpus. 1

In scientific literature, sentences that cite related work can be a valuable resource for applications such as summarization, synonym identification, and entity extraction. In order to determine which equivalent entities are discussed in the various citation sentences, we propose aligning the words within these sentences according to semantic similarity. This problem is partly analogous to the problem of multiple sequence alignment in the biosciences, and is also closely related to the word alignment problem in statistical machine translation. In this paper we address the problem of multiple citation concept alignment by combining and modifying the CRF based pairwise word alignment system of Blunsom & Cohn (2006) and a posterior decoding based multiple sequence alignment algorithm of Schwartz & Pachter (2007). We evaluate the algorithm on hand-labeled data, achieving results that improve on a baseline. 1

All rights reserved.