Abstract | We present a novel semi-supervised training algorithm for learning dependency parsers. |
Abstract | By combining a supervised large margin loss with an unsupervised least squares loss, a dis-criminative, convex, semi-supervised learning algorithm can be obtained that is applicable to large-scale problems. |
Introduction | heavy dependence on annotated corpora—many researchers have investigated semi-supervised learning techniques that can take both labeled and unlabeled training data as input. |
Introduction | Unfortunately, although significant recent progress has been made in the area of semi-supervised learning, the performance of semi-supervised learning algorithms still fall far short of expectations, particularly in challenging real-world tasks such as natural language parsing or machine translation. |
Introduction | A large number of distinct approaches to semi-supervised training algorithms have been investigated in the literature (Bennett and Demiriz, 1998; Zhu et al., 2003; Altun et al., 2005; Mann and McCallum, 2007). |
Abstract | We present a simple and effective semi-supervised method for training dependency parsers. |
Conclusions | In this paper, we have presented a simple but effective semi-supervised learning approach and demonstrated that it achieves substantial improvement over a competitive baseline in two broad-coverage depen- |
Introduction | In this paper, we introduce lexical intermediaries via a simple two-stage semi-supervised approach. |
Introduction | In general, semi-supervised learning can be motivated by two concerns: first, given a fixed amount of supervised data, we might wish to leverage additional unlabeled data to facilitate the utilization of the supervised corpus, increasing the performance of the model in absolute terms. |
Introduction | We show that our semi-supervised approach yields improvements for fixed datasets by performing parsing experiments on the Penn Treebank (Marcus et al., 1993) and Prague Dependency Treebank (Hajic, 1998; Hajic et al., 2001) (see Sections 4.1 and 4.3). |
Related Work | Semi-supervised phrase structure parsing has been previously explored by McClosky et al. |
Experiments and Results | The results for the semi-supervised models are nonconclusive. |
Finding the Homographs in a Lexicon | We experiment with three model setups: Supervised, semi-supervised , and unsupervised. |
Finding the Homographs in a Lexicon | In Model II, the semi-supervised setup, the training data is used to initialize the Expectation-Maximization (EM) algorithm (Dempster et al., 1977) and the unlabeled data, described in Section 3.1, updates the initial estimates. |
Finding the Homographs in a Lexicon | The unsupervised setup, Model III, is similar to the semi-supervised setup except that the EM algorithm is initialized using an informed guess by the authors. |