Enriching News Articles with Related Search Queries

Carmel, David; Fyodorov, Yaroslav; Kuzi, Saar; Mejer, Avihai; Raiber, Fiana; Rainshmidt, Elad

doi:10.1145/3308558.3313588

Cited by 1 publication

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In work on recommending search engine queries to a user reading a document, the queries were either extracted from a query log [5,7,9,19] or were generated based on the document text [24]. Using information induced from a query log [5,9,19,24] and the document itself [5,19,24] can help in recommending queries.…”

Section: Related Workmentioning

confidence: 99%

“…The features used are listed in Table 2. Some of the features quantify surface-level properties, e.g., Len, UniqLen and IMaxLen 7 . Other features quantify properties related to entities, such as IsEnt and ContainEnt.…”

Section: Evaluation 41 Experimental Settingmentioning

confidence: 99%

“…12 All features were min-max normalized. 7 IMaxLen was originally defined as the maximum length of a term in a query [9]; we use the inverse of the maximum length of a term in an n-gram. 8 Kong et al [19] used the term overlap between the query and the title.…”

Section: Evaluation 41 Experimental Settingmentioning

confidence: 99%

See 2 more Smart Citations

Recommending Search Queries in Documents Using Inter N-Gram Similarities

Sheetrit¹,

Fyodorov²,

Raiber³

et al. 2021

Proceedings of the 2021 ACM SIGIR International Conference on Theory of Information Retrieval

Self Cite

View full text Add to dashboard Cite

Reading a document can often trigger a need for additional information. For example, a reader of a news article might be interested in information about the persons and events mentioned in the article. Accordingly, there is a line of work on recommending search-engine queries given a document read by a user. Often, the recommended queries are selected from a query log independently of each other, and are presented to the user without any context. We address a novel query recommendation task where the recommended queries must be n-grams (sequences of consecutive terms) in the document. Furthermore, inspired by work on using inter-document similarities for document retrieval, we explore the merits of using inter n-gram similarities for query recommendation. Specifically, we use a supervised approach to learn an inter n-gram similarity measure where the goal is that n-grams that are likely to serve as queries will be deemed more similar to each other than to other n-grams. We use the similarity measure in a wide variety of query recommendation approaches which we devise as adaptations of ad hoc document retrieval techniques. Empirical evaluation performed using data gathered from Yahoo!'s search engine logs attests to the effectiveness of the resultant recommendation methods.

show abstract