Bayes Risk Minimization in Natural Language Parsing
نویسندگان
چکیده
Candidate selection from n-best lists is a widely used approach in natural language parsing. Instead of attempting to select the most probable candidate, we focus on prediction of a new structure which minimizes an approximation to Bayes risk. Our approach does not place any restrictions on the probabilistic model used. We show how this approach can be applied in both dependency and constituent tree parsing with loss functions standard for these tasks. We evaluate these methods empirically on the Wall Street Journal parsing task.
منابع مشابه
An 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 کاملAltitude Training: Strong Bounds for Single-Layer Dropout
Dropout training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative Poisson topic model with long documents, dropout training improves the exponent in the generalization bound for empirical risk minimization. Dropout achieve...
متن کاملVariational Bayesian Grammar Induction for Natural Language
This paper presents a new grammar induction algorithm for probabilistic context-free grammars (PCFGs). There is an approach to PCFG induction that is based on parameter estimation. Following this approach, we apply the variational Bayes to PCFGs. The variational Bayes (VB) is an approximation of Bayesian learning. It has been empirically shown that VB is less likely to cause overfitting. Moreov...
متن کاملGTI at SemEval-2016 Task 4: Training a Naive Bayes Classifier using Features of an Unsupervised System
This paper presents the approach of the GTI Research Group to SemEval-2016 task 4 on Sentiment Analysis in Twitter, or more specifically, subtasks A (Message Polarity Classification), B (Tweet classification according to a two-point scale) and D (Tweet quantification according to a two-point scale). We followed a supervised approach based on the extraction of features by a dependency parsing-ba...
متن کاملParsing with Neural and Finite Automata Networks: A Graph Grammar Approach
Parsing with finite automata networks implies, in one way, the conversion of a regular expression into a minimal deterministic finite automaton, while parsing with neural networks involves parsing of a natural language sentence. In ‘Parsing with finite automata networks’ finite automata are frequently combined using a set of rules for various operations like union, concatenation, and kleene clo...
متن کامل