No abstract

Semantic slot filling is one of the most challenging problems in spoken language understanding (SLU). In this paper, we propose to use recurrent neural networks (RNNs) for this task, and present several novel architectures designed to efficiently model past and future temporal dependencies. Specifically, we implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants. To facilitate reproducibility, we implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark. In addition, we compared the approaches on two custom SLU data sets from the entertainment and movies domains. Our results show that the RNN-based models outperform the conditional random field (CRF) baseline by 2% in absolute error reduction on the ATIS benchmark. We improve the state-of-the-art by 0.5% in the Entertainment domain, and 6.7% for the movies domain.Index Terms-Recurrent neural network (RNN), slot filling, spoken language understanding (SLU), word embedding.

This paper presents a series of new latent semantic models based on a convolutional neural network (CNN) to learn lowdimensional semantic vectors for search queries and Web documents. By using the convolution-max pooling operation, local contextual information at the word n-gram level is modeled first. Then, salient local features in a word sequence are combined to form a global feature vector. Finally, the high-level semantic information of the word sequence is extracted to form a global vector representation. The proposed models are trained on clickthrough data by maximizing the conditional likelihood of clicked documents given a query, using stochastic gradient ascent. The new models are evaluated on a Web document ranking task using a large-scale, real-world data set. Results show that our model significantly outperforms other semantic models, which were state-of-the-art in retrieval performance prior to this work.

No abstract

Abstract. We propose a novel regularizer when training an auto-encoder for unsupervised feature extraction. We explicitly encourage the latent representation to contract the input space by regularizing the norm of the Jacobian (analytically) and the Hessian (stochastically) of the encoder's output with respect to its input, at the training points. While the penalty on the Jacobian's norm ensures robustness to tiny corruption of samples in the input space, constraining the norm of the Hessian extends this robustness when moving further away from the sample. From a manifold learning perspective, balancing this regularization with the auto-encoder's reconstruction objective yields a representation that varies most when moving along the data manifold in input space, and is most insensitive in directions orthogonal to the manifold. The second order regularization, using the Hessian, penalizes curvature, and thus favors smooth manifold. We show that our proposed technique, while remaining computationally efficient, yields representations that are significantly better suited for initializing deep architectures than previously proposed approaches, beating state-of-the-art performance on a number of datasets.

Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review). In the simplest settings, we discriminate only between positive and negative sentiment, turning the task into a standard binary classification problem. We compare several machine learning approaches to this problem, and combine them to achieve a new state of the art. We show how to use for this task the standard generative language models, which are slightly complementary to the state of the art techniques. We achieve strong results on a well-known dataset of IMDB movie reviews. Our results are easily reproducible, as we publish also the code needed to repeat the experiments. This should simplify further advance of the state of the art, as other researchers can combine their techniques with ours with little effort.

No abstract

Recently, large scale image annotation datasets have been collected with millions of images and thousands of possible annotations. Latent variable models, or embedding methods, that simultaneously learn semantic representations of object labels and image representations can provide tractable solutions on such tasks. In this work, we are interested in jointly learning representations both for the objects in an image, and the parts of those