Stop word recognition method and device
A recognition method and a technology of stop words, applied in the computer field, can solve problems such as increasing requirements, high cost, and inability to adapt to user search behavior, and achieve the effect of improving recognition accuracy
Active Publication Date: 2020-06-16
HUAWEI CLOUD COMPUTING TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] With the widespread use and intelligence of information retrieval systems, more and more users use natural and semi-natural language to input query sentences for search, so the requirements for the stop word recognition ability of information retrieval systems are also increasing. High, the stop word recognition in the prior art is generally realized by the stop word list manually edited by experts in the vocabulary field in advance, and the manually edited stop word list not only has a large production cost, but also relies on matching with the stop word list The method of identifying stop words in the input sentence cannot adapt to the increasingly complex user search behavior
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
[0027] Throughout this manual, the term "stop words", also known as stop words, refers to words in a sentence that do not directly affect the expression of the sentence or have a small impact, such as words in the query sentence entered by the user that are not helpful to search for relevant documents Vocabulary, such as "one" in the query sentence "one basketball player Kobe" is not helpful for retrieving the relevant content that users want, so "one" can be regarded as a stop word in this scenario. It should be noted that in different contexts and application scenarios, whether the same word is a stop word may have different judgments. For example, in the query sentence "one world one dream", if "one" is also removed as a stop word , the accuracy of the search results will be greatly affected.
[002...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
A stop word recognition method relates to the field of computer technology. In this method, after obtaining the first query sentence input by the user, the second query sentence belonging to the same session as the query sentence is obtained, and according to the change characteristics of each word in the first query sentence relative to the second query sentence Stop words in the first query statement are identified. The method can more accurately identify the stop words in the query statement, and improve the recognition accuracy of the stop words.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for identifying stop words used in an information retrieval system and a computing device. Background technique [0002] An information retrieval system, such as a search engine or a question answering (English: question answering) system, retrieves relevant content required by the user according to a query sentence input by the user. The query sentence entered by the user may contain some words that have no practical meaning and occur frequently, also known as stop words (English: stop word). In order to improve the efficiency and accuracy of retrieval, the information retrieval system needs to identify The stop words in the query statement are extracted, and this part of the stop words is removed from the query statement to obtain the keywords in the query statement. The information retrieval system then matches the obtained keywords to obtain the relevant...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F16/2455G06F16/2458G06N20/00
CPCG06F16/00G06F16/2462G06F16/24553G06N20/00
Inventor 周文礼王喆胡斐然
Owner HUAWEI CLOUD COMPUTING TECH CO LTD