Xavier Carreras

Semantic role labeling: an introduction to the special issue

Semantic role labeling, the computational identification and labeling of arguments in text, has become a leading task in computational linguistics today. Although the issues for this task have been studied for decades, the availability of large resources and the development of statistical machine learning methods have heightened the amount of effort in this field. This special issue presents selected and representative work in the field. This overview describes linguistic background of the problem, the movement from linguistic theories to computational practice, the major resources that are being used, an overview of steps taken in computational systems, and a description of the key issues and results in semantic role labeling (as revealed in several international evaluations). We assess weaknesses in semantic role labeling and identify important challenges facing the field. Overall, the opportunities and the potential for useful further research in semantic role labeling are considerable.

TAG, Dynamic Programming, and the Perceptron for Efficient, Feature-Rich Parsing

We describe a parsing approach that makes use of the perceptron algorithm, in conjunction with dynamic programming methods, to recover full constituent-based parse trees. The formalism allows a rich set of parse-tree features, including PCFG-based features, bigram and trigram dependency features, and surface features. A severe challenge in applying such an approach to full syntactic parsing is the efficiency of the parsing algorithms involved. We show that efficient training is feasible, using a Tree Adjoining Grammar (TAG) based parsing formalism. A lower-order dependency parsing model is used to restrict the search space of the full model, thereby making it efficient. Experiments on the Penn WSJ treebank show that the model achieves state-of-the-art performance, for both constituent and dependency accuracy.

An efficient projection for l 1 , ∞ regularization

In recent years the <i>l</i>₁, _∞ norm has been proposed for joint regularization. In essence, this type of regularization aims at extending the <i>l</i>₁ framework for learning sparse models to a setting where the goal is to learn a set of jointly sparse models. In this paper we derive a simple and effective projected gradient method for optimization of <i>l</i>₁, _∞ regularized problems. The main challenge in developing such a method resides on being able to compute efficient projections to the <i>l</i>₁, _∞ ball. We present an algorithm that works in <i>O</i>(<i>n</i> log <i>n</i>) time and <i>O</i>(<i>n</i>) memory where <i>n</i> is the number of parameters. We test our algorithm in a multi-task image annotation problem. Our results show that <i>l</i>₁, _∞ leads to better performance than both <i>l</i>₂ and <i>l</i>₁ regularization and that it is is effective in discovering jointly sparse solutions.

An Empirical Study of Semi-supervised Structured Conditional Models for Dependency Parsing

This paper describes an empirical study of high-performance dependency parsers based on a semi-supervised learning approach. We describe an extension of semi-supervised structured conditional models (SS-SCMs) to the dependency parsing problem, whose framework is originally proposed in (Suzuki and Isozaki, 2008). Moreover, we introduce two extensions related to dependency parsing: The first extension is to combine SS-SCMs with another semi-supervised approach, described in (Koo et al., 2008). The second extension is to apply the approach to second-order parsing models, such as those described in (Carreras, 2007), using a two-stage semi-supervised learning approach. We demonstrate the effectiveness of our proposed methods on dependency parsing experiments using two widely used test collections: the Penn Treebank for English, and the Prague Dependency Tree-bank for Czech. Our best results on test data in the above datasets achieve 93.79% parent-prediction accuracy for English, and 88.05% for Czech.

Non-Projective Parsing for Statistical Machine Translation

We describe a novel approach for syntax-based statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly flexible reordering operations during parsing, in combination with a discriminative model that can condition on rich features of the source-language string. Experiments on translation from German to English show improvements over phrase-based systems, both in terms of BLEU scores and in human evaluations.