The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Extending from limited domain to a new domain is crucial for Natural Language Generation in Dialogue, especially when there are sufficient annotated data in the source domain, but there is little labeled data in the target domain. This paper studies the performance and domain adaptation of two different Neural Network Language Generators in Spoken Dialogue Systems: a gating-based Recurrent Neural...
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models. The main idea is to exploit the Siamese architecture to learn an embedding subspace that is discriminative, and where mapped visual domains are semantically aligned and yet maximally separated. The supervised setting becomes attractive especially when only few...
In recent years, image generation using Convolutional Neural Networks (CNNs) has become increasingly popular in the computer vision domain. However, there is less attention on using CNNs for sprite generation for games. A possible reason for this is that the amount of available sprite data in games is significantly less than in other domains, which typically use hundreds of thousands of images, or...
Representation Learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low dimensional space. There exits two kinds of representation methods for entities in Knowledge Graphs (KGs), including structure-based representation and description-based representation. Most methods represent entities with fact triples of KGs through translating embedding models, which...
In this paper, we introduce Recipe1M, a new large-scale, structured corpus of over 1m cooking recipes and 800k food images. As the largest publicly available collection of recipe data, Recipe1M affords the ability to train high-capacity models on aligned, multi-modal data. Using these data, we train a neural network to find a joint embedding of recipes and images that yields impressive results on...
In this paper we propose a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low complexity. However, most existing hashing methods are designed to preserve one single kind of similarity, thus incapable of dealing with the different tasks simultaneously. To overcome this...
Recent captioning models are limited in their ability to scale and describe concepts unseen in paired image-text corpora. We propose the Novel Object Captioner (NOC), a deep visual semantic captioning model that can describe a large number of object categories not present in existing image-caption datasets. Our model takes advantage of external sources – labeled images from object recognition...
The performance of image retrieval has been improved tremendously in recent years through the use of deep feature representations. Most existing methods, however, aim to retrieve images that are visually similar or semantically relevant to the query, irrespective of spatial configuration. In this paper, we develop a spatial-semantic image search technology that enables users to search for images with...
Multi-view correlation learning has attracted great attention with the proliferation of heterogeneous data. Typical methods, such as Canonical Correlation Analysis (CCA) and its variants, usually maximize one-to-one corresponding correlation of inter-view data, while most of them neglect discriminative multi-label information and local structure of each view data. In this paper, we propose multi-label...
Researchers have done extensive work on establishing an accurate user profile, which has been verified an effective way to implement the user marketing accurately and effectively. In this paper, we will present a feature extraction method based on the fusion of Word2Vec and TF-IDF, and try to establish a user profile. The vector space model (VSM) contains the word vector calculated by Word2Vec, and...
Nowadays, the mobile medical community, providing a communication platform for medical, medical treatment, pharmacy, life science as well as other related domains, acts as a professional social network for doctors, medical institutions, healthcare practitioners and life science. In the medical community, users can ask questions and receive the response from a professional doctor. It is possible to...
Understanding the semantic relations between vision and language data has become a research trend in artificial intelligence and robotic systems. The lack of training data is an essential issue for vision-language understanding. We address the problem of image and sentence cross-modal retrieval when paired training samples are not sufficient. Inspired by recent works in variational inference, in this...
Software defect prediction, which predicts defective code regions, can help developers find bugs and prioritize their testing efforts. To build accurate prediction models, previous studies focus on manually designing features that encode the characteristics of programs and exploring different machine learning algorithms. Existing traditional features often fail to capture the semantic differences...
Predictive modeling using machine learning is an effective method for building compiler heuristics, but there is a shortage of benchmarks. Typical machine learning experiments outside of the compilation field train over thousands or millions of examples. In machine learning for compilers, however, there are typically only a few dozen common benchmarks available. This limits the quality of learned...
Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such...
Although Query-by-Example techniques based on Euclidean distance in a multidimensional feature space have proved to be effective for image databases, this approach cannot be effectively applied to video since the number of dimensions would be massive due to the richness and complexity of video data. The above issue has been addressed in two recent solutions, namely Deterministic Quantization (DQ)...
Latent Dirichlet allocation (LDA) and other modified topic models have become the prevalent tools for semantic analysis and text data mining. With the rapid development of the medical information, large amount of data has been accumulated in the form of text, while most of which recording in a confused structure. Based on LDA, this paper proposes a revised approach, which enlightens an idea of weighting...
The paper presents deep learning models for tweets binary classification. Our approach is based on the Long Short-Term Memory (LSTM) recurrent neural network and hence expects to be able to capture long-term dependencies among words. We develop two models for tweets classification. The basic model, called LSTM-TC, takes word embeddings as input, uses the LSTM layer to derive semantic tweet representation,...
This paper presents a method named SoSVMRank, which integrates the social information of a Web document to generate a high-quality summarization. In order to do that, the summarization was formulated as a learning to rank task, in which the order of a sentence or comment was determined by its informative information. The informative information was measured by a set of local and social features in...
The traditional duplicate bug reports detection approaches are usually based on vector space model. However, the experimental result is rarely satisfying since this method cannot distinguish semantic correlation among bug reports which written by natural languages. Topic model, as a method to model underlying topics of texts, can solve the problem of document similarity calculation methods used in...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.