The Experts below are selected from a list of 74520 Experts worldwide ranked by ideXlab platform
Ming Li - One of the best experts on this subject based on the ideXlab platform.
-
two birds one stone a simple unified model for text generation from structured and Unstructured Data
arXiv: Artificial Intelligence, 2019Co-Authors: Hamidreza Shahidi, Ming LiAbstract:A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and Unstructured Data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and Unstructured Data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks.
-
two birds one stone a simple unified model for text generation from structured and Unstructured Data
arXiv: Artificial Intelligence, 2019Co-Authors: Hamidreza Shahidi, Ming LiAbstract:A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and Unstructured Data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and Unstructured Data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.
Hamidreza Shahidi - One of the best experts on this subject based on the ideXlab platform.
-
two birds one stone a simple unified model for text generation from structured and Unstructured Data
arXiv: Artificial Intelligence, 2019Co-Authors: Hamidreza Shahidi, Ming LiAbstract:A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and Unstructured Data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and Unstructured Data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks.
-
two birds one stone a simple unified model for text generation from structured and Unstructured Data
arXiv: Artificial Intelligence, 2019Co-Authors: Hamidreza Shahidi, Ming LiAbstract:A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and Unstructured Data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and Unstructured Data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.
Yao Zheng - One of the best experts on this subject based on the ideXlab platform.
-
a scalable parallel software volume rendering algorithm for large scale Unstructured Data
International Conference on Conceptual Structures, 2007Co-Authors: Kangjian Wangc, Yao ZhengAbstract:In this paper, we develop a highly accurate parallel software scanned cell projection algorithm (PSSCPA) which is applicable of any classification system. This algorithm could handle both convex and non-convex meshes, and provide maximum flexibilities in applicable types of cells. Compared with previous algorithms using 3D commodity graphics hardware, it introduces no the volume decomposition and rendering artifacts in the resulting images. Finally, high resolution images generated by the algorithm are provided, and the scalability of the algorithm is demonstrated on a PC Cluster with modest parallel resources.
Parul Hooda - One of the best experts on this subject based on the ideXlab platform.
-
Text classification algorithms for mining Unstructured Data: a SWOT analysis
International Journal of Information Technology, 2018Co-Authors: Akshi Kumar, Vikrant Dabas, Parul HoodaAbstract:It has become increasingly crucial and imperative to facilitate knowledge extraction for decision support and deliver targeted information to analysts that span wide application domains. Interestingly, the buzzing term “big Data” which is estimated to be 90% Unstructured further makes it difficult to tap and analyze information with traditional tools. Text mining entails defining a process which transforms and substitutes this Unstructured Data into a structured one to discover knowledge. Use of classification algorithms to intelligently mine text has been studied extensively across literature. This study predominantly surveys the text classification algorithms employed in the process of mining Unstructured Data to report a conclusive analysis on the trend of their use in terms of their respective strengths, weaknesses, opportunities and threats (SWOT). The scope of these algorithms is then explored apropos the application area of sentiment analysis, a typical text classification task. A mapping which determines the unexplored social media technologies and the extent of use of these algorithms within respective social media is proffered to give an insight to the amount of work that has been done in the domain of machine learning based sentiment analysis on social media.
Saul Vargas - One of the best experts on this subject based on the ideXlab platform.
-
product characterisation towards personalisation learning attributes from Unstructured Data to recommend fashion products
Knowledge Discovery and Data Mining, 2018Co-Authors: ângelo Cardoso, Fabio Daolio, Saul VargasAbstract:We describe a solution to tackle a common set of challenges in e-commerce, which arise from the fact that new products are continually being added to the catalogue. The challenges involve properly personalising the customer experience, forecasting demand and planning the product range. We argue that the foundational piece to solve all of these problems is having consistent and detailed information about each product, which is rarely available or consistent given the multitude of suppliers and types of products. We describe in detail the architecture and methodology implemented at ASOS, one of the world's largest fashion e-commerce retailers, to tackle this problem. We then show how this quantitative understanding of the products can be leveraged to improve recommendations in a hybrid recommender system approach.
-
product characterisation towards personalisation learning attributes from Unstructured Data to recommend fashion products
arXiv: Machine Learning, 2018Co-Authors: ângelo Cardoso, Fabio Daolio, Saul VargasAbstract:In this paper, we describe a solution to tackle a common set of challenges in e-commerce, which arise from the fact that new products are continually being added to the catalogue. The challenges involve properly personalising the customer experience, forecasting demand and planning the product range. We argue that the foundational piece to solve all of these problems is having consistent and detailed information about each product, information that is rarely available or consistent given the multitude of suppliers and types of products. We describe in detail the architecture and methodology implemented at ASOS, one of the world's largest fashion e-commerce retailers, to tackle this problem. We then show how this quantitative understanding of the products can be leveraged to improve recommendations in a hybrid recommender system approach.
