In this paper we present a deep-learning system that competed at SemEval-2017 Task 6 “#HashtagWars: Learning a Sense of Humor”. We participated in Subtask A, in which the goal was, given two Twitter messages, to identify which one is funnier. We propose a Siamese architecture with bidirectional Long Short-Term Memory (LSTM) networks, augmented with an attention mechanism. Our system works on th...

The following report introduces ideas augmenting standard Long Short Term Memory (LSTM) architecture with multiple memory cells per hidden unit in order to improve its generalization capabilities. It considers both deterministic and stochastic variants of memory operation. It is shown that the nondeterministic Array-LSTM approach improves stateof-the-art performance on character level text pred...

Temporal relation classification is becoming an active research field. Lots of methods have been proposed, while most of them focus on extracting features from external resources. Less attention has been paid to a significant advance in a closely related task: relation extraction. In this work, we borrow a state-of-the-art method in relation extraction by adopting bidirectional long short-term ...

Aspect-level sentiment classification is a finegrained task in sentiment analysis. Since it provides more complete and in-depth results, aspect-level sentiment analysis has received much attention these years. In this paper, we reveal that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect. For instance, “The appetizers ...

Stock prices are a form of time series data. There have been many existing business and economics based methods for predicting stock prices. These methods can be classed as fundamental and technical analysis. Technical analysis is based on the observing patterns in stock prices based on psychological effects (fear and greed) changing supply and demand. Fundamental analysis is based on observing...

We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model learns to focus selectively on parts of the video frames and classifies videos after taking a few glimpses. The model essentially learns which parts in the fram...

Objective: The present study was hypothesized to investigate the beneficial effects of fresh, aged, and cooked garlic extracts on blood glucose and memory of diabetic rats induced by streptozocine (STZ). Material and Methods: Diabetes was induced by an intraperitoneal injection of STZ (60 mg/kg body weight). An oral dose of 1000 mg/kg of each garlic extract was given daily for 4 weeks after dia...

purpose previous studies have shown that physical activity improves learning and memory. present study was performed to determine the effects of short term and long term treadmill exercise on learning, memory consolidation and retrieval of passive avoidance learning in an animal model. methods in this study fifty male wistar rats with 3-4 months of age were randomly divided into five groups (n=...

The development of new technologies has confronted the entire domain of science and industry with issues of big data's scalability as well as its integration with the purpose of forecasting analytics in its life cycle. In predictive analytics, the forecast of near-future and recent past - or in other words, the now-casting - is the continuous study of real-time events and constantly updated whe...