Product Knowledge Graph Embedding for E-commerce

TL;DR: This paper systematically introduces the existing state-of-the-art approaches and a variety of applications that benefit from these methods in knowledge graph embedding and introduces the advanced models that utilize additional semantic information to improve the performance of the original methods.

TL;DR: The research introduces the related concepts of the knowledge representation and analyzes knowledge representation of knowledge graphs by category, which includes some classical general knowledge graphs and several typical domain knowledge graphs.

TL;DR: In this paper, the authors survey fundamental concepts and practical methods for creating and curating large-scale knowledge bases, including methods for discovering and canonicalizing entities and their semantic types and organizing them into clean taxonomies.

TL;DR: In this article, the authors survey fundamental concepts and practical methods for creating and curating large-scale knowledge bases, including methods for discovering and canonicalizing entities and their semantic types and organizing them into clean taxonomies.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

TL;DR: It is conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and it is proposed to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.

TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.

TL;DR: In this paper, the authors propose to use a soft-searching model to find the parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly.