Bilingual Projection of Dependency Grammar | So we extract projected discrete dependency arc instances instead of treebank as training set for the projected grammar induction model. |
Bilingually-Guided Dependency Grammar Induction | This section presents our bilingually-guided grammar induction model, which incorporates unsuperVised framework and bilingual projection model through a joint approach. |
Bilingually-Guided Dependency Grammar Induction | According to following observation: unsuperVised induction model mines underlying syntactic structure of the monolingual language, however, it is hard to find good grammar induction in the exponential parsing space; bilingual projection obtains relatively reliable syntactic knowledge of the |
Bilingually-Guided Dependency Grammar Induction | Based on the idea, we propose a novel strategy for training monolingual grammar induction model with the guidance of unsupervised and bilingually-projected dependency information. |
Conclusion and Future Work | This paper presents a bilingually-guided strategy for automatic dependency grammar induction , which adopts an unsupervised skeleton and leverages the bilingually-projected dependency information during optimization. |
Experiments | The results in Figure 3 prove that our unsupervised framework 04 = 1 can promote the grammar induction if it has a good start (well initialization), and it will be better once we incorporate the information from the projection side (04 = 0.9). |
Introduction | Dependency Grammar Induction |
Introduction | In dependency grammar induction , unsupervised methods achieve continuous improvements in recent years (Klein and Manning, 2004; Smith and Eisner, 2005; Bod, 2006; William et al., 2009; Spitkovsky et al., 2010). |
Introduction | In the rest of the paper, we first describe the unsupervised dependency grammar induction framework in section 2 (where the unsupervised optimization objective is given), and introduce the bilingual projection method for dependency parsing in section 3 (where the projected optimization objective is given); Then in section 4 we present the bilingually-guided induction strategy for dependency grammar (where the two objectives above are jointly optimized, as shown in Figure 1). |
Discussion | In principle, our branch-and-bound method can approach e-optimal solutions to Viterbi training of locally normalized generative models, including the NP-hard case of grammar induction with the DMV. |
Introduction | dency grammar induction ). |
Introduction | This is evident for grammar induction . |
Introduction | (2010b) present evidence that hard EM can outperform soft EM for grammar induction in a hill-climbing setting. |
Related Work | Alas, there are not yet any spectral learning methods that recover latent tree structure, as in grammar induction . |
Related Work | Several integer linear programming (ILP) formulations of dependency parsing (Riedel and Clarke, 2006; Martins et al., 2009; Riedel et al., 2012) inspired our definition of grammar induction as a MP. |
Relaxations | In this section, we will show how the RLT can be applied to our grammar induction problem and contrast it with the concave envelope relaxation presented in section 4.2. |
Conclusion | The most important direction of future work for OSTAG is the development of a principled grammar induction model, perhaps using the same techniques that have been successfully applied to TSG and TIG. |
Experiments | A compact TSG can be obtained automatically using the MCMC grammar induction technique of Cohn and Blunsom (2010), retaining all TSG rules that appear in at least one derivation in after 1000 iterations of sampling. |
Experiments | While our grammar induction method is a crude (but effective) heuristic, we can still highlight the qualities of the more important auxiliary trees by examining aggregate statistics over the MPD parses, shown in Figure 6. |
TAG and Variants | This model has proven effective for grammar induction via Markov Chain Monte Carlo (MCMC), in which TSG derivations of the training set are repeatedly sampled to find frequently occurring elementary trees. |
TAG and Variants | However, a large effort in non-probabilistic grammar induction has been performed through manual annotation with the XTAG project(Doran et al., 1994). |
TAG and Variants | Later approaches (Shindo et al., 2011; Yamangil and Shieber, 2012) were able to extend the nonparametric modeling of TSGs to TIG, providing methods for both modeling and grammar induction . |
Bayesian inference for PCFGs | 9 Empirical effects of the three approaches in unsupervised grammar induction |
Bayesian inference for PCFGs | In this section we present experiments using the three samplers just described in an unsupervised grammar induction problem. |
Bayesian inference for PCFGs | Our goal here is not to improve the state-of-the-art in unsupervised grammar induction , but to try to measure empirical differences in the estimates produced by the three different approaches to tightness just described. |
Cohesion across Utterances | 3.4 Grammar Induction |
Cohesion across Utterances | The grammar g of surface realisation candidates is obtained through an automatic grammar induction algorithm which can be run on unlabelled data and requires only minimal human intervention. |
Cohesion across Utterances | We provide the human corpus of restaurant recommendations from Section 3.3 as input to grammar induction . |
Evaluation | Algorithm 1 Grammar Induction . |
Experiments | The first one (spiIZ) is the DMV-based grammar inducer by Spitkovsky et al. |
Introduction | The task of unsupervised dependency parsing (which strongly relates to the grammar induction task) has become popular in the last decade, and its quality has been greatly increasing during this period. |
Related Work | Such approaches achieve better results; however, they are useless for grammar induction from plain text. |