Álvaro Peris

Video Description Using Bidirectional Recurrent Neural Networks

Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions. The combination of Convolutional and Recurrent Neural Networks in these models has proven to outperform the previous state of the art, obtaining more accurate video descriptions. In this work we propose pushing further this model by introducing two contributions into the encoding stage. First, producing richer image representations by combining object and location information from Convolutional Neural Networks and second, introducing Bidirectional Recurrent Neural Networks for capturing both forward and backward temporal relationships in the input frames.

Egocentric video description based on temporally-linked sequences

Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover daily patterns for improving the quality of life of the user. A natural topic that arises in egocentric vision is storytelling, that is, how to understand and tell the story relying behind the pictures. In this paper, we tackle storytelling as an egocentric sequences description problem. We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences. Furthermore, we present a new method for multimodal data fusion consisting on a multi-input attention recurrent network. We also publish the first dataset for egocentric image sequences description, consisting of 1,339 events with 3,991 descriptions, from 55 days acquired by 11 people. Furthermore, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description.

VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question Answering

In this paper, we address the problem of visual question answering by proposing a novel model, called VIBIKNet. Our model is based on integrating Kernelized Convolutional Neural Networks and Long-Short Term Memory units to generate an answer given a question about an image. We prove that VIBIKNet is an optimal trade-off between accuracy and computational load, in terms of memory and time consumption. We validate our method on the VQA challenge dataset and compare it to the top performing methods in order to illustrate its performance and speed.

Neural Networks Classifier for Data Selection in Statistical Machine Translation

Abstract Corpora are precious resources, as they allow for a proper estimation of statistical machine translation models. Data selection is a variant of the domain adaptation field, aimed to extract those sentences from an out-of-domain corpus that are the most useful to translate a different target domain. We address the data selection problem in statistical machine translation as a classification task. We present a new method, based on neural networks, able to deal with monolingual and bilingual corpora. Empirical results show that our data selection method provides slightly better translation quality, compared to a state-of-the-art method (cross-entropy), requiring substantially less data. Moreover, the results obtained are coherent across different language pairs, demonstrating the robustness of our proposal.

Segment-based interactive-predictive machine translation

Machine translation systems require human revision to obtain high-quality translations. Interactive methods provide an efficient human–computer collaboration, notably increasing productivity. Recently, new interactive protocols have been proposed, seeking for a more effective user interaction with the system. In this work, we present one of these new protocols, which allows the user to validate all correct word sequences in a translation hypothesis. Thus, the left-to-right barrier from most of the existing protocols is broken. We compare this protocol against the classical prefix-based approach, obtaining a significant reduction of the user effort in a simulated environment. Additionally, we experiment with the use of confidence measures to select the word the user should correct at each iteration, reaching the conclusion that the order in which words are corrected does not affect the overall effort.

NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning

Abstract We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.