Joseph P. Turian

Learn More
If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word representations as extra word features. We evaluate Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words on both NER and chunking. We use near state-of-the-art supervised baselines, and(More)
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements. Theano is being actively(More)
Theano is a compiler for mathematical expressions in Python that combines the convenience of NumPy’s syntax with the speed of optimized native machine language. The user composes mathematical expressions in a high-level description that mimics NumPy’s syntax and semantics, while being statically typed and functional (as opposed to imperative). These(More)
DeSR is a statistical transition-based dependency parser which learns from annotated corpora which actions to perform for building parse trees while scanning a sentence. We describe recent improvements to the parser, in particular stacked parsing, exploiting a beam search strategy and using a Multilayer Perceptron classifier. For the Evalita 2009 Dependency(More)
Discriminative training methods have recently led to significant advances in the state of the art of machine translation (MT). Another promising trend is the incorporation of syntactic information into MT systems. Combining these trends is difficult for reasons of system complexity and computational complexity. The present study makes progress towards a(More)
Parsing and translating natural languages can be viewed as problems of predicting tree structures. For machine learning approaches to these predictions, the diversity and high dimensionality of the structures involved mandate very large training sets. This paper presents a purely discriminative learning method that scales up well to problems of this size.(More)
The present work advances the accuracy and training speed of discriminative parsing. Our discriminative parsing method has no generative component, yet surpasses a generative baseline on constituent parsing, and does so with minimal linguistic cleverness. Our model can incorporate arbitrary features of the input and parse state, and performs feature(More)
We use different word representations as word features for a named-entity recognition (NER) system with a linear model. This work is part of a larger empirical survey, evaluating different word representations on different NLP tasks. We evaluate Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words. All(More)