Qin Iris Wang

Learn More
We present a novel semi-supervised training algorithm for learning dependency parsers. 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. To demonstrate the benefits of this approach, we apply the(More)
Recently, significant progress has been made on learning structured predictors via coordinated training algorithms such as conditional random fields and maximum margin Markov networks. Unfortunately , these techniques are based on specialized training algorithms, are complex to implement, and expensive to run. We present a much simpler approach to training(More)
We present an improved approach for learning dependency parsers from tree-bank data. Our technique is based on two ideas for improving large margin training in the context of dependency parsing. First, we incorporate local constraints that enforce the correctness of each individual link, rather than just scoring the global parse tree. Second, to cope with(More)
My research is focused on developing machine learning algorithms for inferring dependency parsers from language data. By investigating several approaches I have developed a unifying perspective that allows me to share advances between both probabilistic and non-probabilistic methods. First, I describe a generative technique that uses a strictly lexicalised(More)
Data-driven (statistical) approaches have been playing an increasingly prominent role in parsing since the 1990s. In recent years, there has been a growing interest in dependency-based as opposed to constituency-based approaches to syntactic parsing, with application to a wide range of research areas and different languages. Graph-based and transition-based(More)
This paper proposes a structure that automatically analyzes the parameters of Chinese test items. This structure utilizes latent semantic analysis (LSA) to analyze the relationships of keywords among all test items in an item bank. It also uses the similarity measure to calculate the similarity degree of keywords. We also propose an algorithm, which is(More)
A progressive image compression approach based on integer wavelet transform (IWT) and grey prediction is proposed. The compression approach is combining the EZW method and a grey prediction to compress images. IWT adopts lifting scheme and the grey prediction is based on the grey theory to further improve the compression rate withou degrading the image(More)