Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attentio...

Vector Auto-regressive models (VAR) are useful tools for analyzing time series data. In quite a few modern time series modelling tasks, the collection of reliable time series turns out to be a major challenge, either due to the slow progression of the dynamic process of interest, or inaccessibility of repetitive measurements of the same dynamic process over time. In those situations, however, w...

In this work we present a state-of-the-art approach for unconstrained natural scene text recognition. We propose a cascade approach that incorporates a convolutional neural network (CNN) architecture followed by a long short term memory model (LSTM). The CNN learns visual features for the characters and uses them with a softmax layer to detect sequence of characters. While the CNN gives very go...

Morphological inflection generation is the task of generating the inflected form of a given lemma corresponding to a particular linguistic transformation. We model the problem of inflection generation as a character sequence to sequence learning problem and present a variant of the neural encoder-decoder model for solving it. Our model is language independent and can be trained in both supervis...

While Active Learning (AL) has already been shown to markedly reduce the annotation efforts for many sequence labeling tasks compared to random selection, AL remains unconcerned about the internal structure of the selected sequences (typically, sentences). We propose a semisupervised AL approach for sequence labeling where only highly uncertain subsequences are presented to human annotators, wh...

The problem of labeling (or segmenting) sequences is very important in many applications such as part-of-speech tagging in natural language processing, multimodal object detection in computer vision, and DNA/protein structure prediction in bioinformatics. Conditional Random Fields (CRFs) of [1] are known to be the best sequence models ever for the problem. CRF is a conditional model, P (s|y), i...

An interactive Question Answering (QA) system frequently encounters non-sentential (incomplete) questions. These non-sentential questions may not make sense to the system when a user asks them without the context of conversation. The system thus needs to take into account the conversation context to process the incomplete question. In this work, we present a recurrent neural network (RNN) based...

External memory has been proven to be essential for the success of neural network-based systems on many tasks, including Question-Answering, classification, machine translation and reasoning. In all those models the memory is used to store instance representations of multiple levels, analogous to “data” in the Von Neumann architecture of a computer, while the “instructions” are stored in the we...

The sequence to sequence architecture is widely used in the response generation and neural machine translation to model the potential relationship between two sentences. It typically consists of two parts: an encoder that reads from the source sentence and a decoder that generates the target sentence word by word according to the encoder’s output and the last generated word. However, it faces t...