Topic
Word embedding
About: Word embedding is a research topic. Over the lifetime, 4683 publications have been published within this topic receiving 153378 citations. The topic is also known as: word embeddings.
Papers
More filters
TL;DR: The classification model was trained to learn the classification of consequence severity levels in high-quality HAZOP analysis reports, which will not only ensure the consistency of the analysis results, but also help smaller chemical plants perform security analysis.
18 citations
20 Mar 2016
TL;DR: This paper studies user modeling in proactive search systems and proposes a learning to rank method for proactive ranking, and proposes semantic similarity features using word embedding and an entity taxonomy in knowledge base to reduce the feature sparsity problem in entity modeling.
Abstract: Proactive search systems like Google Now and Microsoft Cortana have gained increasing popularity with the growth of mobile Internet. Unlike traditional reactive search systems where search engines return results in response to queries issued by the users, proactive systems actively push information cards to the users on mobile devices based on the context around time, location, environment (e.g., weather), and user interests. A proactive system is a zero-query information retrieval system, which makes user modeling critical for understanding user information needs. In this paper, we study user modeling in proactive search systems and propose a learning to rank method for proactive ranking. We explore a variety of ways of modeling user interests, ranging from direct modeling of historical interaction with content types to finer-grained entity-level modeling, and user demographical information. To reduce the feature sparsity problem in entity modeling, we propose semantic similarity features using word embedding and an entity taxonomy in knowledge base. Experiments performed with data from a large commercial proactive search system show that our method significantly outperforms a strong baseline method deployed in the production system.
18 citations
TL;DR: This work proposes a similarity metric Convolutional Neural Network (CNN) based on a channel attention model for traffic anomaly detection task and shows that the proposed method is three percentage points higher than deep convolutional generative adversarial network (DCGAN) and five percentage pointsHigher than AutoEncoder on the accuracy.
Abstract: In recent years, with the development of the Internet of Things (IoT) technology, a large amount of data can be captured from sensors for real-time analysis. By monitoring the traffic video data from the IoT, we can detect the anomalies that may occur and evaluate the security. However, the number of traffic anomalies is extremely limited, so there is a severe over-fitting problem when using traditional deep learning methods. In order to solve the problem above, we propose a similarity metric Convolutional Neural Network (CNN) based on a channel attention model for traffic anomaly detection task. The method mainly includes (1) A Siamese network with a hierarchical attention model by word embedding so that it can selectively measure similarities between anomalies and the templates. (2) A deep transfer learning method can automatically annotate an unlabeled set while fine-tuning the network. (3) A background modeling method combining spatial and temporal information for anomaly extraction. Experiments show that the proposed method is three percentage points higher than deep convolutional generative adversarial network (DCGAN) and five percentage points higher than AutoEncoder on the accuracy. No more time consumption is needed for the annotation process. The extracted candidates can be classified correctly through the proposed method.
18 citations
28 Aug 2018
TL;DR: A deep learning based ensemble model for intent detection where the outputs of different deep learning architectures such as convolutional neural network (CNN) and variants of recurrent neural networks (RNN) like long short term memory (LSTM) and gated recurrent units (GRU) are combined together using a multi-layer perceptron (MLP).
Abstract: One of the significant task in spoken language understanding (SLU) is intent detection. In this paper, we propose a deep learning based ensemble model for intent detection. The outputs of different deep learning architectures such as convolutional neural network (CNN) and variants of recurrent neural networks (RNN) like long short term memory (LSTM) and gated recurrent units (GRU) are combined together using a multi-layer perceptron (MLP). The classifiers are trained using a combined word embedding representation obtained from both Word2Vec and Glove. Our experiments on the benchmark ATIS dataset show state-of-the-art performance for intent detection.
18 citations
02 Sep 2021
TL;DR: The authors discuss and compare two of the most recent word embedding models for text classification and present a technical comparison of the two models for the task text classification, and compare their performance.
Abstract: Text Classification is one of the most cited applications of Natural Language Processing. Classification can save the cost of manual efforts and at the same time increase the accuracy of a task. With multiple advancements in language modeling techniques over the last two decades, a number of word embedding models have been proposed. In this study, we discuss and compare two of the most recent models for the task text classification and present a technical comparison.
18 citations