Query Spelling Correction
2020
In this chapter we will focus on the discussion of an important type of query understandings: Query spelling correction, especially on the web search queries. Queries issued by web search engine users usually contain errors and misused words/phrases. Although a user might have a clear intent in her mind, inferring the query’s intent in this case becomes difficult because of the edit errors or vocabulary gap between the user’s ideal query and the query issued to the search engine. Because of this, query spelling correction is a crucial component of modern search engines. The performance of the query spelling correction component will affect all other parts of the search engine. In this chapter we will first introduce early works on query spelling correction based on edit distance. Then we will discuss the noisy channel model to the problem. After that we will introduce modern approaches to more complex and realistic problem setup where it involves multiple types of spelling errors. Finally we will also summarize other components needed to support a modern large-scale query spelling correction system.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
29
References
1
Citations
NaN
KQI