With the development and progress of today’s network information technology,a variety of large-scale network databases have emerged with the situation,such as Baidu Library and Weipu Database,the number of documents ...With the development and progress of today’s network information technology,a variety of large-scale network databases have emerged with the situation,such as Baidu Library and Weipu Database,the number of documents in the inventory has reached nearly one million.So how do you quickly and effectively retrieve the information you want in such a huge database?This requires finding efficient algorithms to reduce the computational complexity of the computer during Information Retrieval,improve retrieval efficiency,and adapt to the rapid expansion of document data.The Quicksort Algorithm gives different weights to each position of the document,and multiplies the weight of each position with the number of matches of that position,and then adds all the multiplied sums to set a feature value for Quicksort,which can achieve the full accuracy of Information Retrieval.Therefore,the purpose of this paper is to use the quick sort algorithm to increase the speed of Information Retrieval,and to use the position weighting algorithm to improve the matching quality of Information Retrieval,so as to achieve the overall effect of improving the efficiency of Information Retrieval.展开更多
ChatGPT has attracted extension attention of academia and industry.This paper aims to evaluate ChatGPT in Chinese language understanding capability on 6 tasks using 11 datasets.Experiments indicate that ChatGPT achiev...ChatGPT has attracted extension attention of academia and industry.This paper aims to evaluate ChatGPT in Chinese language understanding capability on 6 tasks using 11 datasets.Experiments indicate that ChatGPT achieved competitive results in sentiment analysis,summary,and reading comprehension in Chinese,while it is prone to factual errors in closed-book QA.Further,on two more difficult Chinese understanding tasks,that is,idiom fill-in-the-blank and cants understanding,we found that a simple chain-of-thought prompt can improve the accuracy of ChatGPT in complex reasoning.This paper further analyses the possible risks of using ChatGPT based on the results.Finally,we briefly describe the research and development progress of our ChatBIT.展开更多
基金This work was supported in part by the National Natural Science Foundation of China,Grant No.72073041Open Foundation for the University Innovation Platform in the Hunan Province,Grant No.18K103.2011+2 种基金Collaborative Innovation Center for Development and Utilization of Finance and Economics Big Data Property.Hunan Provincial Key Laboratory of Finance&Economics Big Data Science and Technology2020 Hunan Provincial Higher Education Teaching Reform Research Project under Grant HNJG-2020-1130,HNJG-2020-11242020 General Project of Hunan Social Science Fund under Grant 20B16.
文摘With the development and progress of today’s network information technology,a variety of large-scale network databases have emerged with the situation,such as Baidu Library and Weipu Database,the number of documents in the inventory has reached nearly one million.So how do you quickly and effectively retrieve the information you want in such a huge database?This requires finding efficient algorithms to reduce the computational complexity of the computer during Information Retrieval,improve retrieval efficiency,and adapt to the rapid expansion of document data.The Quicksort Algorithm gives different weights to each position of the document,and multiplies the weight of each position with the number of matches of that position,and then adds all the multiplied sums to set a feature value for Quicksort,which can achieve the full accuracy of Information Retrieval.Therefore,the purpose of this paper is to use the quick sort algorithm to increase the speed of Information Retrieval,and to use the position weighting algorithm to improve the matching quality of Information Retrieval,so as to achieve the overall effect of improving the efficiency of Information Retrieval.
文摘ChatGPT has attracted extension attention of academia and industry.This paper aims to evaluate ChatGPT in Chinese language understanding capability on 6 tasks using 11 datasets.Experiments indicate that ChatGPT achieved competitive results in sentiment analysis,summary,and reading comprehension in Chinese,while it is prone to factual errors in closed-book QA.Further,on two more difficult Chinese understanding tasks,that is,idiom fill-in-the-blank and cants understanding,we found that a simple chain-of-thought prompt can improve the accuracy of ChatGPT in complex reasoning.This paper further analyses the possible risks of using ChatGPT based on the results.Finally,we briefly describe the research and development progress of our ChatBIT.
