Learn More
Learning from imbalanced data sets, where the number of examples of one (majority) class is much higher than the others, presents an important challenge to the machine learning community. Traditional machine learning algorithms may be biased towards the majority class, thus producing poor predictive accuracy over the minority class. In this paper, we(More)
The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation. In this paper, we propose to extend it to tree structures, in which a memory cell can reflect the history memories of multiple child cells or multiple descendant cells in a recursive process. We call(More)
Multirelational classification aims at discovering useful patterns across multiple inter-connected tables (relations) in a relational database. Many traditional learning techniques, however, assume a single table or a flat file as input (the so-called propositional algorithms). Existing multirelational classification approaches either “upgrade” mature(More)
Negation words, such as no and not, play a fundamental role in modifying sentiment of textual expressions. We will refer to a negation word as the negator and the text span within the scope of the negator as the argument. Commonly used heuristics to estimate the sentiment of negated expressions rely simply on the sentiment of argument (and not on the(More)
We examined patterns of habitat function (plant species richness), productivity (plant aboveground biomass and total C), and nutrient stocks (N and P in aboveground plant biomass and soil) in tidal marshes of the Satilla, Altamaha, and Ogeechee Estuaries in Georgia, USA. We worked at two sites within each salinity zone (fresh, brackish, and saline) in each(More)
Our submission to the W-NUT Named Entity Recognition in Twitter task closely follows the approach detailed by Cherry and Guo (2015), who use a discriminative, semi-Markov tagger, augmented with multiple word representations. We enhance this approach with updated gazetteers, and with infused phrase embeddings that have been adapted to better predict the(More)
Many species are expanding their distributions to higher latitudes due to global warming. Understanding the mechanisms underlying these distribution shifts is critical for better understanding the impacts of climate changes. The climate envelope approach is widely used to model and predict species distribution shifts with changing climates. Biotic(More)
Understanding of how plant communities are organized and will respond to global changes requires an understanding of how plant species respond to multiple environmental gradients. We examined the mechanisms mediating the distribution patterns of tidal marsh plants along an estuarine gradient in Georgia (USA) using a combination of field transplant(More)