Query performance prediction refers to inferring retrieval performance of a given query with a search engine. It is useful in a few different ways. For example, if a given query has poor performance, then the search engine may give the user an alert. Thus the initial query can be modified for better performance. It is also possible that the search engine may modify a query automatically. Poor performance to certain type of queries also indicates that there are not enough relevant documents in the corpus and more relevant documents to these queries should be replenished.
Query performance prediction methods can be classified into three categories: post-retrieval prediction, pre-retrieval prediction, and combination methods. Post-retrieval prediction happens when the retrieval results are obtained. It involves the use of contents, relevance scores, and many other features of retrieved results. Pre-retrieval performance prediction uses the descriptive features (such as linguistic features and part-of-speech tags) of query terms, corpus related statistics, and others to predict query performance.
The prediction process happens before the retrieval process takes place, and retrieval results are not required. The third category is combination methods which combine different prediction methods or features into one. Recently, some machine learning methods such as neural networks have also been used in many information retrieval tasks including query performance prediction. The major task is to set up a beneficial prediction model.
A related issue is how to select a group of most useful features from a large number of them. For both post-retrieval prediction and pre-retrieval prediction, dozens of features can be collected.
To undertake this project, it is desirable to have good knowledge on information retrieval, machine learning, and statistical analysis.
Vice Chancellors Research Scholarships (VCRS)
The scholarships will cover tuition fees and a maintenance award of £14,777 per annum for three years (subject to satisfactory academic performance). Applications are invited from UK, European Union and overseas students.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 14,777 per annum for three years. EU applicants will only be eligible for the fees component of the studentship (no maintenance award is provided). For Non EU nationals the candidate must be "settled" in the UK.
As Senior Engineering Manager of Analytics at Seagate Technology I utilise the learning from my PhD ever day
Adrian Johnston - PhD in InformaticsWatch Video
Monday 18 February 2019
25 to 29 March 2019
The largest of Ulster's campuses
When applying for this PhD opportunity please quote reference number: