We discuss the relevance of k-best parsing to recent applications in natural language processing, and develop efficient algorithms for k-best trees in the framework of hypergraph parsing. To demonstrate the efficiency, scalability and accuracy of these algorithms, we present experiments on Bikel’s implementation of Collins ’ lexicalized PCFG model, and on Chiang’s CFG-based decoder for hierarchical phrase-based translation. We show in particular how the improved output of our algorithms has the potential to improve results from parse reranking systems and other applications. 1

Systems based on synchronous grammars and tree transducers promise to improve the quality of statistical machine translation output, but are often very computationally intensive. The complexity is exponential in the size of individual grammar rules due to arbitrary re-orderings between the two languages. We develop a theory of binarization for synchronous context-free grammars and present a linear-time algorithm for binarizing synchronous rules when possible. In our large-scale experiments, we found that almost all rules are binarizable and the resulting binarized rule set significantly improves the speed and accuracy of a state-of-the-art syntaxbased machine translation system. We also discuss the more general, and computationally more difficult, problem of finding good parsing strategies for non-binarizable rules, and present an approximate polynomial-time algorithm for this problem. 1.

Weighted deduction with aggregation is a powerful theoretical formalism that encompasses many NLP algorithms. This paper proposes a declarative specification language, Dyna; gives general agenda-based algorithms for computing weights and gradients; briefly discusses Dyna-to-Dyna program transformations; and shows that a first implementation of a Dyna-to-C++ compiler produces code that is efficient enough for real NLP research, though still several times slower than hand-crafted code. 1

Dynamic Programming (DP) is an important class of algorithms widely used in many areas of speech and language processing. Recently there have been a series of work trying to formalize many instances of DP algorithms under algebraic and graph-theoretic frameworks. This tutorial surveys two such frameworks, namely semirings and directed hypergraphs, and draws connections between them. We formalize two particular types of DP algorithms under each of these frameworks: the Viterbi-style topological algorithms and the Dijkstra-style best-first algorithms. Wherever relevant, we also discuss typical applications of these algorithms in Natural Language Processing. 1

We describe the application of the graph-theoretic property known as treewidth to the problem of finding efficient parsing algorithms. This method, similar to the junction tree algorithm used in graphical models for machine learning, allows automatic discovery of efficient algorithms such as the O(n 4) algorithm for bilexical grammars of Eisner and Satta. We examine the complexity of applying this method to parsing algorithms for general Linear Context-Free Rewriting Systems. We show that any polynomial-time algorithm for this problem would imply an improved approximation algorithm for the well-studied treewidth problem on general graphs. 1.

There is one and only one complete analysis of the sentence. (my translation) Die Sprache verkleidet den Gedanken. Und zwar so, daß man nach der äußeren Form des Kleides, nicht auf die Form des bekleideten Gedankens schließen kann; weil die äußere Form des Kleides nach ganz anderen Zwecken gebildet ist als danach, die Form des Körpers erkennen zu lassen. Die stillschweigenden Abmachungen zum Verständnis der Umgangssprache sind enorm kompliziert. — Wittgenstein (TLP 4.002) Language veils thought. And in such a manner that by the form of the cloak one cannot

Abstract not found

Users want natural language processing (NLP) systems to be both fast and accurate, but quality often comes at the cost of speed. The field has been manually exploring various speed-accuracy tradeoffs for particular problems or datasets. We aim to explore this space automatically, focusing here on the case of agenda-based syntactic parsing (Kay, 1986). Unfortunately, offthe-shelf reinforcement learning techniques fail to learn good policies: the state space is too large to explore naively. We propose a hybrid reinforcement/apprenticeship learning algorithm that, even with few inexpensive features, can automatically learn weights that achieve competitive accuracies at significant improvements in speed over state-of-the-art baselines. 1.