LSTM (Long Short-Term Memory) recurrent neural networks have been highly successful in a number of application areas. This technical report describes the use of the MNIST and UW3 databases for benchmarking LSTM networks and explores the effect of different architectural and hyperparameter choices on performance. Significant findings include: (1) LSTM performance depends smoothly on learning rat...

We propose a dialogue state tracker based on long short term memory (LSTM) neural networks. LSTM is an extension of a recurrent neural network (RNN), which can better consider distant dependencies in sequential input. We construct a LSTM network that receives utterances of dialogue participants as input, and outputs the dialogue state of the current utterance. The input utterances are separated...

We aim to learn hypernymy present in distributed word representations using a deep LSTM neural network. We hypothesize that the semantic information of hypernymy is distributed differently across the components of the hyponym and hypernym vectors for varying examples of hypernymy. We use an LSTM cell with a replacement gate to adjust the state of the network as different examples of hypernymy a...

In this paper we implemented different models to solve the review usefulness classification problem. Both feed-forward neural network and LSTM were able to beat the baseline model. Performances of the models are evaluated using 0-1 loss and F-1 scores. In general, LSTM outperformed feed-forward neural network, as we trained our own word vectors in that model, and LSTM itself was able to store m...

In this paper, we explore the possibility of leveraging Residual Networks (ResNet), a powerful structure in constructing extremely deep neural network for image understanding, to improve recurrent neural networks (RNN) for modeling sequential data. We show that for sequence classification tasks, incorporating residual connections into recurrent structures yields similar accuracy to Long Short T...

Video caption refers to generating a descriptive sentence for a specific short video clip automatically, which has achieved remarkable success recently. However, most of the existing methods focus more on visual information while ignoring the synchronized audio cues. We propose three multimodal deep fusion strategies to maximize the benefits of visual-audio resonance information. The first one ...

Recently, Recurrent Neural Network (RNN) solutions for recommender systems (RS) are becoming increasingly popular. The insight is that, there exist some intrinsic patterns in the sequence of users’ actions, and RNN has been proved to perform excellently when modeling sequential data. In traditional tasks such as language modeling, RNN solutions usually only consider the sequential order of obje...

This paper addresses the problem of geometric scene parsing, i.e. simultaneously labeling geometric surfaces (e.g. sky, ground and vertical plane) and determining the interaction relations (e.g. layering, supporting, siding and affinity) between main regions. This problem is more challenging than the traditional semantic scene labeling, as recovering geometric structures necessarily requires th...

English. In this paper we describe our approach to EVALITA 2016 POS tagging for Italian Social Media Texts (PoSTWITA). We developed a two-branch bidirectional Long Short Term Memory recurrent neural network, where the first bi-LSTM uses a typical vector representation for the input words, while the second one uses a newly introduced word-vector representation able to encode information about th...

Script identification plays a significant role in analysing documents and videos. In this paper, we focus on the problem of script identification in scene text images and video scripts. Because of low image quality, complex background and similar layout of characters shared by some scripts like Greek, Latin, etc., text recognition in those cases become challenging. Most of the recent approaches...