Institution
Alibaba Group
Company•Hangzhou, China•
About: Alibaba Group is a company organization based out in Hangzhou, China. It is known for research contribution in the topics: Computer science & Terminal (electronics). The organization has 6810 authors who have published 7389 publications receiving 55653 citations. The organization is also known as: Alibaba Group Holding Limited & Alibaba Group (Cayman Islands).
Topics: Computer science, Terminal (electronics), Graph (abstract data type), Node (networking), Deep learning
Papers published on a yearly basis
Papers
More filters
••
01 Jun 2019TL;DR: This work highlights several pitfalls associated with learning under such a setup in the context of NER and proposes a novel yet easy-to-implement approach for recognizing named entities with incomplete data annotations.
Abstract: Supervised approaches to named entity recognition (NER) are largely developed based on the assumption that the training data is fully annotated with named entity information. However, in practice, annotated data can often be imperfect with one typical issue being the training data may contain incomplete annotations. We highlight several pitfalls associated with learning under such a setup in the context of NER and identify limitations associated with existing approaches, proposing a novel yet easy-to-implement approach for recognizing named entities with incomplete data annotations. We demonstrate the effectiveness of our approach through extensive experiments.
58 citations
•
27 Aug 2007TL;DR: In this paper, Wu et al. proposed a method for displaying web pages based on a correspondence relationship between a data block identifier and the data block, which can be used to greatly reduce the pressure on a server end, save network bandwidth resources, and improve a client's speed for displaying a web page.
Abstract: Disclosed is a method for displaying a web page. According to the method, upon receiving a data block including web page display data from a server, a client stores a data block identifier and a correspondence relationship between the data block identifier and the data block. The client then uses the identifier of the needed data block to determine whether the needed data block identifier is stored in the client, if affirmative, obtains the data block corresponding to the found data block identifier according to the correspondence relationship, and displays the web page display data of the obtained data block on a web page. Further discloses a system for displaying a web page. The disclosed method and system can be used to greatly reduce the pressure on a server end, save network bandwidth resources, and improve a client's speed for displaying a web page.
58 citations
••
TL;DR: Wang et al. as discussed by the authors proposed a novel GNN-based method, Relational Reflection Entity Alignment (RREA), to obtain relation specific embeddings for each entity in a more efficient way.
Abstract: Entity alignment aims to identify equivalent entity pairs from different Knowledge Graphs (KGs), which is essential in integrating multi-source KGs. Recently, with the introduction of GNNs into entity alignment, the architectures of recent models have become more and more complicated. We even find two counter-intuitive phenomena within these methods: (1) The standard linear transformation in GNNs is not working well. (2) Many advanced KG embedding models designed for link prediction task perform poorly in entity alignment. In this paper, we abstract existing entity alignment methods into a unified framework, Shape-Builder & Alignment, which not only successfully explains the above phenomena but also derives two key criteria for an ideal transformation operation. Furthermore, we propose a novel GNNs-based method, Relational Reflection Entity Alignment (RREA). RREA leverages Relational Reflection Transformation to obtain relation specific embeddings for each entity in a more efficient way. The experimental results on real-world datasets show that our model significantly outperforms the state-of-the-art methods, exceeding by 5.8%-10.9% on Hits@1.
58 citations
•
TL;DR: This work proposes a novel and generic time series decomposition algorithm that extracts the trend component robustly by solving a regression problem using the least absolute deviations loss with sparse regularization and applies the non-local seasonal filtering to extract the seasonality component.
Abstract: Decomposing complex time series into trend, seasonality, and remainder components is an important task to facilitate time series anomaly detection and forecasting. Although numerous methods have been proposed, there are still many time series characteristics exhibiting in real-world data which are not addressed properly, including 1) ability to handle seasonality fluctuation and shift, and abrupt change in trend and reminder; 2) robustness on data with anomalies; 3) applicability on time series with long seasonality period. In the paper, we propose a novel and generic time series decomposition algorithm to address these challenges. Specifically, we extract the trend component robustly by solving a regression problem using the least absolute deviations loss with sparse regularization. Based on the extracted trend, we apply the the non-local seasonal filtering to extract the seasonality component. This process is repeated until accurate decomposition is obtained. Experiments on different synthetic and real-world time series datasets demonstrate that our method outperforms existing solutions.
58 citations
••
01 Jun 2019TL;DR: A novel Bi-directional Selective Encoding with Template (BiSET) model, which leverages template discovered from training data to softly select key information from each source article to guide its summarization process, is proposed.
Abstract: The success of neural summarization models stems from the meticulous encodings of source articles. To overcome the impediments of limited and sometimes noisy training data, one promising direction is to make better use of the available training data by applying filters during summarization. In this paper, we propose a novel Bi-directional Selective Encoding with Template (BiSET) model, which leverages template discovered from training data to softly select key information from each source article to guide its summarization process. Extensive experiments on a standard summarization dataset are conducted and the results show that the template-equipped BiSET model manages to improve the summarization performance significantly with a new state of the art.
58 citations
Authors
Showing all 6829 results
Name | H-index | Papers | Citations |
---|---|---|---|
Philip S. Yu | 148 | 1914 | 107374 |
Lei Zhang | 130 | 2312 | 86950 |
Jian Xu | 94 | 1366 | 52057 |
Wei Chu | 80 | 670 | 28771 |
Le Song | 76 | 345 | 21382 |
Yuan Xie | 76 | 739 | 24155 |
Narendra Ahuja | 76 | 474 | 29517 |
Rong Jin | 75 | 449 | 19456 |
Beng Chin Ooi | 73 | 408 | 19174 |
Wotao Yin | 72 | 303 | 27233 |
Deng Cai | 70 | 326 | 24524 |
Xiaofei He | 70 | 260 | 28215 |
Irwin King | 67 | 476 | 19056 |
Gang Wang | 65 | 373 | 21579 |
Xiaodan Liang | 61 | 318 | 14121 |