Generating query substitutions

By Rosie Jones, Benjamin Rey, Omid Madani, Wiley Greiner. The Web Conference, 2006

738 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/d0fd30ce8d311cb97725670b5a176cec8ac71677

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Systems

Citations in the corpus

Query suggestion using hitting time (2008, methodology): “While there are quite a few work on generating different types of query suggestions, such as query auto completion [7, 8], query spelling correction [10, 15], query expansion [21, 22, 3], and query rewriting [1, 13].”
The query-flow graph: model and applications (2008, methodology): “Similar queries can be obtained by replacing the query as a whole, or by substituting constituent phrases [16].”
Similarity Measures for Short Segments of Text (2007, methodology): “…our techniques on a query-query similarity task, it should be noted that this problem, and the related problem of suggesting and identifying query-query reformulations has been investigated from a number of angles, ranging from machine learning approaches [4] to query session log analysis[2].”
LambdaMerge: merging the results of query reformulations (2011, methodology): “Candidate reformulations for a query can be collected from sources such as user session rewrites [16, 17], anchortext [18, 9], word co-occurrence in documents [27, 30], click graphs [6, 32] or combination of multiple sources [13].”
Recurrent Convolutional Neural Networks for Discourse Compositionality (2013, background): “To this end much work has been done on modelling the meaning of single words by way of semantic vectors (Turney and Pantel, 2010; Collobert and Weston, 2008) and the latter have found applicability in areas such as information retrieval (Jones et al., 2006).”
Bilingual Word Embeddings for Phrase-Based Machine Translation (2013, methodology): “On NIST08 Chinese-English translation task, we obtain an improvement of 0.48 BLEU from a competitive base-line (30.01 BLEU to 30.49 BLEU) with the Stanford Phrasal MT system.”
Privacy in Search Logs (2009, background): “[10], related queries for a query are identified in two steps.”
Investigating behavioral variability in web search (2007, background): “Other applications of these logs have been in the prediction patterns of search on temporal patterns of query refinement [17], or the use of these logs in query suggestion [16].”
Modeling and solving term mismatch for full-text retrieval (2012, methodology): “Recent IR research is seeing a gradual increase in structured expansion or query reformulation, both in academia and in industry (Lamping and Baker 2005; Jones et al. 2006).”
SearchTogether: an interface for collaborative web search (2007, methodology): “Examples from this line of work include systems that use query logs and clickthrough data to generate query substitutions or recommendations, such as [2] and [15].”
Mining Query Logs: Turning Search Usage Data into Knowledge (2010, methodology): “For this reason in [121] they set the log likelihood ratio threshold to a high level of 100 thus making the method highly selective and precise.”
Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods (2010, methodology): “…years, the information retrieval community has extensively explored the task of query expansion by applying paraphrasing techniques to generate similar or related queries (Beeferman and Berger 2000; Jones et al. 2006; Sahami and Hellman 2006; Metzler, Dumais, and Meek 2007; Shi and Yang 2007).”
A Dual Embedding Space Model for Document Ranking (2016, background): “There may even be insufficient behaviour data to learn a click-based embedding [18] or a translation model [10, 19].”
Semantic Matching in Search (2014, background): “The features of the ranking model include mutual information between queries as in [96], edit distance between queries, and an extended edit distance between queries which takes semantic similarity into consideration.”
A Survey of Automatic Query Expansion in Information Retrieval (2012, background): “…help identify useful associations, such as considering queries that occurred in the same session (e.g., successive queries issued by a single user [Jones et al. 2006]) or queries that yielded similar sets of presumably relevant documents (e.g., by deploying the bipartite graph induced by…”
DeepIntent: Learning Attentions for Online Advertising with Recurrent Neural Networks (2016, background): “[13] uses point-wise mutual information to determine whether a phrase stands out comparing to adjacent terms.”