Collaborating Authors

Adaptive Multi-Compositionality for Recursive Neural Models with Applications to Sentiment Analysis

AAAI Conferences

Recursive neural models have achieved promising results in many natural language processing tasks. The main difference among these models lies in the composition function, i.e., how to obtain the vector representation for a phrase or sentence using the representations of words it contains. This paper introduces a novel Adaptive Multi-Compositionality (AdaMC) layer to recursive neural models. The basic idea is to use more than one composition functions and adaptively select them depending on the input vectors. We present a general framework to model each semantic composition as a distribution over these composition functions. The composition functions and parameters used for adaptive selection are learned jointly from data. We integrate AdaMC into existing recursive neural models and conduct extensive experiments on the Stanford Sentiment Treebank. The results illustrate that AdaMC significantly outperforms state-of-the-art sentiment classification methods. It helps push the best accuracy of sentence-level negative/positive classification from 85.4% up to 88.5%.

How to Visualize Data Composition - DZone Big Data


One of the most common uses of charts is illustrating part-to-whole relationships, aka. Pie charts may be the most popular chart type for this purpose, but other chart types may be just as good (or much better). In this article, we will look at ways to effectively communicate parts-to-whole relationships effectively using pie, donut, sunburst, stacked bar/column, stacked area, and treemap charts. Which chart to use is primarily driven by the nature of the data. As a rule of thumb, for simple datasets (six or fewer elements), a pie or donut chart works well.

Semantic Composition and Decomposition: From Recognition to Generation Artificial Intelligence

Semantic composition is the task of understanding the meaning of text by composing the meanings of the individual words in the text. Semantic decomposition is the task of understanding the meaning of an individual word by decomposing it into various aspects (factors, constituents, components) that are latent in the meaning of the word. We take a distributional approach to semantics, in which a word is represented by a context vector. Much recent work has considered the problem of recognizing compositions and decompositions, but we tackle the more difficult generation problem. For simplicity, we focus on noun-modifier bigrams and noun unigrams. A test for semantic composition is, given context vectors for the noun and modifier in a noun-modifier bigram ("red salmon"), generate a noun unigram that is synonymous with the given bigram ("sockeye"). A test for semantic decomposition is, given a context vector for a noun unigram ("snifter"), generate a noun-modifier bigram that is synonymous with the given unigram ("brandy glass"). With a vocabulary of about 73,000 unigrams from WordNet, there are 73,000 candidate unigram compositions for a bigram and 5,300,000,000 (73,000 squared) candidate bigram decompositions for a unigram. We generate ranked lists of potential solutions in two passes. A fast unsupervised learning algorithm generates an initial list of candidates and then a slower supervised learning algorithm refines the list. We evaluate the candidate solutions by comparing them to WordNet synonym sets. For decomposition (unigram to bigram), the top 100 most highly ranked bigrams include a WordNet synonym of the given unigram 50.7% of the time. For composition (bigram to unigram), the top 100 most highly ranked unigrams include a WordNet synonym of the given bigram 77.8% of the time.

iPromoter-BnCNN: a Novel Branched CNN Based Predictor for Identifying and Classifying Sigma Promoters Machine Learning

Promoter is a short region of DNA which is responsible for initiating transcription of specific genes. Development of computational tools for automatic identification of promoters is in high demand. According to the difference of functions, promoters can be of different types. Promoters may have both intra and inter class variation and similarity in terms of consensus sequences. Accurate classification of various types of sigma promoters still remains a challenge. We present iPromoter-BnCNN for identification and accurate classification of six types of promoters - sigma24, sigma28, sigma32, sigma38, sigma54, sigma70. It is a Convolutional Neural Network (CNN) based classifier which combines local features related to monomer nucleotide sequence, trimer nucleotide sequence, dimer structural properties and trimer structural properties through the use of parallel branching. We conducted experiments on a benchmark dataset and compared with two state-of-the-art tools to show our supremacy on 5-fold cross-validation. Moreover, we tested our classifier on an independent test dataset. Our proposed tool iPromoter-BnCNN along with the source code is freely available at

Titanium isotopic evidence for felsic crust and plate tectonics 3.5 billion years ago


Earth exhibits a dichotomy in elevation and chemical composition between the continents and ocean floor. We measured the titanium isotopic composition of shales to constrain the chemical composition of the continental crust exposed to weathering and found that shales of all ages have a uniform isotopic composition. This can only be explained if the emerged crust was predominantly felsic (silica-rich) since 3.5 billion years ago, requiring an early initiation of plate tectonics. We also observed a change in the abundance of biologically important nutrients phosphorus and nickel across the Archean-Proterozoic boundary, which might have helped trigger the rise in atmospheric oxygen.