This paper proposes a combination of a convolutional and a LSTM network to improve the accuracy of OCR on early printed books. While the standard model of line based OCR uses a single LSTM layer, we utilize a CNNand Pooling-Layer combination in advance of an LSTM layer. Due to the higher amount of trainable parameters the performance of the network relies on a high amount of training examples t...

This is part II of three-part work. Here, we present a second set of inter-related five variants of simplified Long Short-term Memory (LSTM) recurrent neural networks by further reducing adaptive parameters. Two of these models have been introduced in part I of this work. We evaluate and verify our model variants on the benchmark MNIST dataset and assert that these models are comparable to the ...

Wikipedia is the largest online encyclopedia that allows anyone to edit articles. In this paper, we propose the use of deep learning to detect vandals based on their edit history. In particular, we develop a multi-source long-short term memory network (M-LSTM) to model user behaviors by using a variety of user edit aspects as inputs, including the history of edit reversion information, edit pag...

Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL) models that generalizes the earlier work Zaheer et al. (2017) of combining topic models with LSTM. However, unlike ...

Nowadays, online data shows an astonishing increase and the issue of semantic indexing remains an open question. Ontologies and knowledge bases have been widely used to optimize performance. However, researchers are placing increased emphasis on internal relations of ontologies but neglect latent semantic relations between ontologies and documents. They generally annotate instances mentioned in...

This paper describes a simple and efficient Neural Language Model approach for text classification that relies only on unsupervised word representation inputs. Our model employs Recurrent Neural Network Long Short-Term Memory (RNN-LSTM), on top of pre-trained word vectors for sentence-level classification tasks. In our hypothesis we argue that using word vectors obtained from an unsupervised ne...

Recently, feedforward sequential memory networks (FSMN) has shown strong ability to model past and future long-term dependency in speech signals without using recurrent feedback, and has achieved better performance than BLSTM in acoustic modeling. However, the encoding coefficients in FSMN is context-independent while context-dependent weights are commonly supposed to be more reasonable in acou...

Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This ...

Inspired by recent advances in neural machine translation, that jointly align and translate using encoder-decoder networks equipped with attention, we propose an attentionbased LSTM model for human activity recognition. Our model jointly learns to classify actions and highlight frames associated with the action, by attending to salient visual information through a jointly learned soft-attention...

This project is one of the research topics in Professor William Dally’s group. In this project, we developed a pruning based method to learn both weights and connections for Long Short Term Memory (LSTM). In this method, we discard the unimportant connections in a pretrained LSTM, and make the weight matrix sparse. Then, we retrain the remaining model. After we remaining model is converge, we p...