Spectral Dependency Parsing with Latent Variables
نویسندگان
چکیده
Recently there has been substantial interest in using spectral methods to learn generative sequence models like HMMs. Spectral methods are attractive as they provide globally consistent estimates of the model parameters and are very fast and scalable, unlike EM methods, which can get stuck in local minima. In this paper, we present a novel extension of this class of spectral methods to learn dependency tree structures. We propose a simple yet powerful latent variable generative model for dependency parsing, and a spectral learning method to efficiently estimate it. As a pilot experimental evaluation, we use the spectral tree probabilities estimated by our model to re-rank the outputs of a near state-of-the-art parser. Our approach gives us a moderate reduction in error of upto 4.6% over the baseline re-ranker.
منابع مشابه
Transition-based dependency parsing as latent-variable constituent parsing
We provide a theoretical argument that a common form of projective transitionbased dependency parsing is less powerful than constituent parsing using latent variables. The argument is a proof that, under reasonable assumptions, a transition-based dependency parser can be converted to a latent-variable context-free grammar producing equivalent structures.
متن کاملBenchmarking of Statistical Dependency Parsers for French
We compare the performance of three statistical parsing architectures on the problem of deriving typed dependency structures for French. The architectures are based on PCFGs with latent variables, graph-based dependency parsing and transition-based dependency parsing, respectively. We also study the influence of three types of lexical information: lemmas, morphological features, and word cluste...
متن کاملA Latent Variable Model for Generative Dependency Parsing
We propose a generative dependency parsing model which uses binary latent variables to induce conditioning features. To define this model we use a recently proposed class of Bayesian Networks for structured prediction, Incremental Sigmoid Belief Networks. We demonstrate that the proposed model achieves state-of-the-art results on three different languages. We also demonstrate that the features ...
متن کاملAn improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملA Latent Variable Model of Synchronous Syntactic-Semantic Parsing for Multiple Languages
Motivated by the large number of languages (seven) and the short development time (two months) of the 2009 CoNLL shared task, we exploited latent variables to avoid the costly process of hand-crafted feature engineering, allowing the latent variables to induce features from the data. We took a pre-existing generative latent variable model of joint syntacticsemantic dependency parsing, developed...
متن کامل