Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms.However, the dimensions of dense embedding spaces are not designed to resemble human semantic knowledge.Moreover, embeddings are often built from a single source of information (typically text data), even though neurocognitive research suggests that semantics is deeply linked to both language and perception.In this paper, we combine multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint Non-Negative Sparse Embedding.Through indepth analyses comparing these sparse models to human-derived behavioural and neuroimaging data, we demonstrate their ability to predict interpretable linguistic descriptions of human ground-truth semantic knowledge.

The brain is the locus of our language ability, and so brain images can be used to ground linguistic theories.Here we introduce Brain-Bench, a lightweight system for testing distributional models of word semantics.We compare the performance of several models, and show that the performance on brain-image tasks differs from the performance on behavioral tasks.We release our benchmark test as part of a web service.

Alona Fyshe, Leila Wehbe, Partha P. Talukdar, Brian Murphy, Tom M. Mitchell. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

Vector space models (VSMs) represent word meanings as points in a high dimensional space. VSMs are typically created using a large text corpora, and so represent word semantics as observed in text. We present a new algorithm (JNNSE) that can incorporate a measure of semantics not previously used to create VSMs: brain activation data recorded while people read words. The resulting model takes advantage of the complementary strengths and weaknesses of corpus and brain activation data to give a more complete representation of semantics. Evaluations show that the model 1) matches a behavioral measure of semantics more closely, 2) can be used to predict corpus data for unseen words and 3) has predictive power that generalizes across brain imaging technologies and across subjects. We believe that the model is thus a more faithful representation of mental vocabularies.

How can we correlate the neural activity in the human brain as it responds to typed words, with properties of these terms (like ‘edible’, ‘fits in hand’)? In short, we want to find latent variables, that jointly explain both the brain activity, as well as the behavioral responses. This is one of many settings of the Coupled Matrix-Tensor Factorization (CMTF) problem. Can we accelerate any CMTF solver, so that it runs within a few minutes instead of tens of hours to a day, while maintaining good accuracy? We introduce Turbo-SMT, a meta-method capable of doing exactly that: it boosts the performance of any CMTF algorithm, by up to 200x, along with an up to 65 fold increase in sparsity, with comparable accuracy to the baseline. We apply Turbo-SMT to BrainQ, a dataset consisting of a (nouns, brain voxels, human subjects) tensor and a (nouns, properties) matrix, with coupling along the nouns dimension. Turbo-SMT is able to find meaningful latent variables, as well as to predict brain activity with competitive accuracy.

The XML data is order-sensitive. The order problem, that is how ordered XML documents and order-sensitive queries over it can be efficiently supported when mapped into the unordered relational data model, has not yet been adequately addressed. In this paper, we present a general approach for supporting order-sensitive XQuery-to-SQL translation that works irrespective of the chosen XML-to-relational data mapping and the selected order-encoding method. Our approach, called XSOT, utilizes an order-aware XML algebra representation. We propose order-sensitive rewriting rules at the algebraic level to eliminate the dependency of the order determining operators on the implicit XML view order. Furthermore, we introduce a series of order-sensitive optimization steps to transform the XML algebra tree for the purpose of efficient SQL translation. Lastly, we utilize a template-based approach using SQL-99 order features to generate SQL statements.

No abstract available.

No abstract available.