An information-theoretic approach to automatic query expansion

By Claudio Carpineto, R. Mori, Giovanni Romano, B. Bigi. ACM Trans. Inf. Syst., 2001

421 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/d53a4e272f75e9badb997fff98637ddcd9dac824

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

1. Jian-Yun Nie
2. Akshay Deepak
3. Dr. Hiteshwar Kumar Azad
4. W. Bruce Croft
5. Ji-rong Wen
6. Giovanni Romano
7. Claudio Carpineto
8. Wolfgang Nejdl

In Information Systems

1. Akshay Deepak
2. Dr. Hiteshwar Kumar Azad
3. Giovanni Romano
4. Claudio Carpineto
5. Jian-Yun Nie
6. W. Bruce Croft
7. Ji-rong Wen
8. Wei-Ying Ma

In Signal Processing

1. Akshay Deepak
2. Dr. Hiteshwar Kumar Azad
3. Giovanni Romano
4. Claudio Carpineto
5. Jian-Yun Nie
6. W. Bruce Croft
7. Ji-rong Wen
8. Fang Wen

Citations in the corpus

• Personalized query expansion for the web (2007, background): “[4] maximized the divergence between the language model defined by the top retrieved documents and that defined by the entire collection.”
• Well Begun Is Half Done: Generating High-Quality Seeds for Automatic Image Dataset Construction from Web (2014, positive): “(ii) We utilize automatic query expansion [2].”
• Query Expansion by Mining User Logs (2003, methodology): “[7] presented a method of weighting and selecting expansion terms using Information Theory.”
• A Survey of Automatic Query Expansion in Information Retrieval (2012, methodology): “…easy (dif.cult) queries do not necessarily pro­duce better (worse) performance, as there is no clear correlation between the average precision that the original query achieves and by how much AQE improves average precision [Billerbeck and Zobel 2003; Carpineto et al. 2001; He and Ounis 2009b].”
• Predicting query performance (2002, background): “Mori, Romano, and Bigi[ 3 ] use a weight very similar to the individual term contributions to the clarity score of a query (as shown in Figure 2, for example) to rank and weight terms within Rocchio query expansion.”
• Novelty and diversity in information retrieval evaluation (2008, neutral): “[12].”
• Query Expansion Techniques for Information Retrieval: a Survey (2017, positive): “It has been commonly shown that the effectiveness of the query expansion decreases minutely with the non-optimum number of expansion terms [57].”