Applying Data Mining to Pseudo-Relevance Feedback for High Performance Text Retrieval

Huang, Xiangji; Huang, Yan Rui; Wen, Miao; An, Aijun; Liu, Yang; Poon, Josiah

doi:10.1109/icdm.2006.22

Cited by 34 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It assumes that topranked documents in the first-pass retrieval are relevant, and then used as feedback documents in order to refine the representation of original queries by adding potentially related terms. Although PRF has been shown to be effective in improving IR performance [4,6,9,13,23,26,28,30,36,37,40,42] in a number of IR tasks, traditional PRF can also fail in some cases. For example, when some of the feedback documents have several incoherent topics, terms in the irrelevant contents are likely to misguide the feedback models by importing noisy terms into the queries.…”

Section: Introductionmentioning

confidence: 98%

Proximity-based rocchio's model for pseudo relevance

Miao

Huang

Zheng

2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Rocchio's relevance feedback model is a classic query expansion method and it has been shown to be effective in boosting information retrieval performance. The selection of expansion terms in this method, however, does not take into account the relationship between the candidate terms and the query terms (e.g., term proximity). Intuitively, the proximity between candidate expansion terms and query terms can be exploited in the process of query expansion, since terms closer to query terms are more likely to be related to the query topic.In this paper, we study how to incorporate proximity information into the Rocchio's model, and propose a proximitybased Rocchio's model, called PRoc, with three variants. In our PRoc models, a new concept (proximity-based term frequency, ptf ) is introduced to model the proximity information in the pseudo relevant documents, which is then used in three kinds of proximity measures. Experimental results on TREC collections show that our proposed PRoc models are effective and generally superior to the state-of-the-art relevance feedback models with optimal parameters. A direct comparison with positional relevance model (PRM) on the GOV2 collection also indicates our proposed model is at least competitive to the most recent progress.

show abstract

Section: Introductionmentioning

confidence: 98%

Proximity-based rocchio's model for pseudo relevance

Miao

Huang

Zheng

2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…Most of the work on PRF used the top ranked documents or passages [Ruthven and Lalmas 2003;Xu and Croft 2000] as pseudo-relevant documents (or positive examples). Some researchers chose to include also pseudo-nonrelevant documents (or negative examples), by using the bottom-ranked documents [Huang et al 2006;Yan et al 2003], while others found no improvement in doing so [Buckley and Robertson 2008;Kaptein et al 2008]. We chose to use both positive and negative examples, as the initial query representation includes irrelevant concepts to be removed (for which we believe negative examples will be useful), in addition to missing relevant concepts (for which the positive examples alone are sufficient).…”

Section: Feature Selection Using Pseudo-relevance Feedbackmentioning

confidence: 99%

Concept-Based Information Retrieval Using Explicit Semantic Analysis

Egozi

Markovitch

Gabrilovich

2011

ACM Trans. Inf. Syst.

225

122

View full text Add to dashboard Cite

Information retrieval systems traditionally rely on textual keywords to index and retrieve documents. Keyword-based retrieval may return inaccurate and incomplete results when different keywords are used to describe the same concept in the documents and in the queries. Furthermore, the relationship between these related keywords may be semantic rather than syntactic, and capturing it thus requires access to comprehensive human world knowledge. Concept-based retrieval methods have attempted to tackle these difficulties by using manually built thesauri, by relying on term cooccurrence data, or by extracting latent word relationships and concepts from a corpus. In this article we introduce a new concept-based retrieval approach based on Explicit Semantic Analysis (ESA), a recently proposed method that augments keywordbased text representation with concept-based features, automatically extracted from massive human knowledge repositories such as Wikipedia. Our approach generates new text features automatically, and we have found that high-quality feature selection becomes crucial in this setting to make the retrieval more focused. However, due to the lack of labeled data, traditional feature selection methods cannot be used, hence we propose new methods that use self-generated labeled training data. The resulting system is evaluated on several TREC datasets, showing superior performance over previous state-of-the-art results.

show abstract

“…Request permissions from permissions@acm.org. ous studies have shown the benefits brought by transductive learning for IR [24,14,13,9,17,26,31]. Most of these previous approaches assume the top-ranked documents to be highly relevant to the given query, and is closely related to the query topic.…”

Section: Introductionmentioning

confidence: 99%

Clustering-based transduction for learning a ranking model with limited human labels

Zhang

Luo

et al. 2013

Proceedings of the 22nd ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Transductive learning is a semi-supervised learning paradigm that can leverage unlabeled data by creating pseudo labels for learning a ranking model, when there is only limited or no training examples available. However, the effectiveness of transductive learning in information retrieval (IR) can be hindered by the low quality pseudo labels. To this end, we propose to incorporate a two-step k-means clustering algorithm to select the high quality training queries for generating the pseudo labels. In particular, the first step selects the high-quality queries for which the relevant documents are highly coherent as indicated by the clustering results. The second step then selects the initial training examples for the transductive learning that iteratively aggregating the pseudo examples. Finally, the learning to rank (LTR) algorithms are applied to learn the ranking model using the pseudo training examples created by the transductive learning process. Our proposed approach is particularly suitable for applications where there is only little or no human labels available as it does not necessarily involve the use of relevance assessments information or human efforts. Experimental results on the standard TREC Tweets11 collection show that our proposed approach outperforms strong baselines, namely the conventional applications of learning to rank algorithms using human labels for the training and transductive learning using all the queries available.

show abstract

Applying Data Mining to Pseudo-Relevance Feedback for High Performance Text Retrieval

Cited by 34 publications

References 21 publications

Proximity-based rocchio's model for pseudo relevance

Proximity-based rocchio's model for pseudo relevance

Concept-Based Information Retrieval Using Explicit Semantic Analysis

Clustering-based transduction for learning a ranking model with limited human labels

Contact Info

Product

Resources

About