Learn More
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It(More)
There is rising interest in vector-space word embeddings and their use in NLP, especially given recent methods for their fast estimation at very large scale. Nearly all this work, however, assumes a single vector per word type—ignoring poly-semy and thus jeopardizing their usefulness for downstream tasks. We present an extension to the Skip-gram model that(More)
Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as a byproduct generate highly informative vector representations for words, known as word em-beddings. In this paper we present two(More)
Multitask learning algorithms are typically designed assuming some fixed, a priori known latent structure shared by all the tasks. However, it is usually unclear what type of latent task structure is the most appropriate for a given multitask learning problem. Ideally, the " right " latent task structure should be learned in a data-driven manner. We present(More)
Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints , where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other(More)
Linear chains and trees are basic building blocks in many applications of graphi-cal models, and they admit simple exact maximum a-posteriori (MAP) inference algorithms based on message passing. However, in many cases this computation is prohibitively expensive, due to quadratic dependence on variables' domain sizes. The standard algorithms are inefficient(More)
Dual decomposition provides the opportunity to build complex, yet tractable, structured prediction models using linear constraints to link together submodels that have available MAP inference routines. However, since some constraints might not hold on every single example, such models can often be improved by relaxing the requirement that these constraints(More)
Automated harmonic analysis is an important and interesting music research topic. Although many researchers have studied solutions to this problem, there is no comprehensive and systematic comparison of the many techniques proposed. In this paper we present Rameau, a framework for automatic harmonic analysis we are developing. With Rameau we are able to(More)
We employ universal schema for slot filling and cold start. In universal schema, we allow each surface pattern from raw text, and each type defined in ontology, i.e. TACKBP slots to represent relations. And we use matrix factorization to discover implications among surface patterns and target slots. First, we identify mentions of entities from the whole(More)
Relation extraction by universal schema avoids mapping to a brittle, incomplete traditional schema by instead making predictions in the union of all input schemas, including tex-tual patterns. Modeling these predictions by matrix competition with matrix factorization has yielded state-of-the-art accuracies. One difficulty with prior work in matrix(More)