LDA-Based Document Models for Ad-hoc Retrieval. Wei, X. & Croft, W., B.
Paper
Website abstract bibtex Search algorithms incorporating some form of topic model have a long history in information retrieval. For example, cluster-based retrieval has been studied since the 60s and has recently produced good results in the language model framework. An approach to building topic models based on a formal generative model of documents, Latent Dirichlet Allocation (LDA), is heavily cited in the machine learning literature, but its feasibility and effectiveness in information retrieval is mostly unknown. In this paper, we study how to efficiently use LDA to improve ad-hoc retrieval. We propose an LDA-based document model within the language modeling framework, and evaluate it on several TREC collections. Gibbs sampling is employed to conduct approximate inference in LDA and the computational complexity is analyzed. We show that improvements over retrieval using cluster-based models can be obtained with reasonable efficiency.
@article{
title = {LDA-Based Document Models for Ad-hoc Retrieval},
type = {article},
keywords = {Document Model,Experimentation Keywords Information Retrieval,Language Model,Latent Dirichlet Allocation (LDA),Topic Model},
websites = {http://delivery.acm.org/10.1145/1150000/1148204/p178-wei.pdf?ip=128.227.11.255&id=1148204&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517849765_76c2307841baea334709cecf679f9fb3},
id = {cfa87390-76cf-3e19-9cfa-ced2749d8105},
created = {2018-02-05T16:51:16.103Z},
accessed = {2018-02-05},
file_attached = {true},
profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},
group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},
last_modified = {2018-02-05T16:51:18.465Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {Search algorithms incorporating some form of topic model have a long history in information retrieval. For example, cluster-based retrieval has been studied since the 60s and has recently produced good results in the language model framework. An approach to building topic models based on a formal generative model of documents, Latent Dirichlet Allocation (LDA), is heavily cited in the machine learning literature, but its feasibility and effectiveness in information retrieval is mostly unknown. In this paper, we study how to efficiently use LDA to improve ad-hoc retrieval. We propose an LDA-based document model within the language modeling framework, and evaluate it on several TREC collections. Gibbs sampling is employed to conduct approximate inference in LDA and the computational complexity is analyzed. We show that improvements over retrieval using cluster-based models can be obtained with reasonable efficiency.},
bibtype = {article},
author = {Wei, Xing and Croft, W Bruce}
}
Downloads: 0
{"_id":"G556syTMaKmTootg4","bibbaseid":"wei-croft-ldabaseddocumentmodelsforadhocretrieval","downloads":0,"creationDate":"2018-02-07T16:22:57.267Z","title":"LDA-Based Document Models for Ad-hoc Retrieval","author_short":["Wei, X.","Croft, W., B."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"LDA-Based Document Models for Ad-hoc Retrieval","type":"article","keywords":"Document Model,Experimentation Keywords Information Retrieval,Language Model,Latent Dirichlet Allocation (LDA),Topic Model","websites":"http://delivery.acm.org/10.1145/1150000/1148204/p178-wei.pdf?ip=128.227.11.255&id=1148204&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517849765_76c2307841baea334709cecf679f9fb3","id":"cfa87390-76cf-3e19-9cfa-ced2749d8105","created":"2018-02-05T16:51:16.103Z","accessed":"2018-02-05","file_attached":"true","profile_id":"371589bb-c770-37ff-8193-93c6f25ffeb1","group_id":"f982cd63-7ceb-3aa2-ac7e-a953963d6716","last_modified":"2018-02-05T16:51:18.465Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"Search algorithms incorporating some form of topic model have a long history in information retrieval. For example, cluster-based retrieval has been studied since the 60s and has recently produced good results in the language model framework. An approach to building topic models based on a formal generative model of documents, Latent Dirichlet Allocation (LDA), is heavily cited in the machine learning literature, but its feasibility and effectiveness in information retrieval is mostly unknown. In this paper, we study how to efficiently use LDA to improve ad-hoc retrieval. We propose an LDA-based document model within the language modeling framework, and evaluate it on several TREC collections. Gibbs sampling is employed to conduct approximate inference in LDA and the computational complexity is analyzed. We show that improvements over retrieval using cluster-based models can be obtained with reasonable efficiency.","bibtype":"article","author":"Wei, Xing and Croft, W Bruce","bibtex":"@article{\n title = {LDA-Based Document Models for Ad-hoc Retrieval},\n type = {article},\n keywords = {Document Model,Experimentation Keywords Information Retrieval,Language Model,Latent Dirichlet Allocation (LDA),Topic Model},\n websites = {http://delivery.acm.org/10.1145/1150000/1148204/p178-wei.pdf?ip=128.227.11.255&id=1148204&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517849765_76c2307841baea334709cecf679f9fb3},\n id = {cfa87390-76cf-3e19-9cfa-ced2749d8105},\n created = {2018-02-05T16:51:16.103Z},\n accessed = {2018-02-05},\n file_attached = {true},\n profile_id = {371589bb-c770-37ff-8193-93c6f25ffeb1},\n group_id = {f982cd63-7ceb-3aa2-ac7e-a953963d6716},\n last_modified = {2018-02-05T16:51:18.465Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {Search algorithms incorporating some form of topic model have a long history in information retrieval. For example, cluster-based retrieval has been studied since the 60s and has recently produced good results in the language model framework. An approach to building topic models based on a formal generative model of documents, Latent Dirichlet Allocation (LDA), is heavily cited in the machine learning literature, but its feasibility and effectiveness in information retrieval is mostly unknown. In this paper, we study how to efficiently use LDA to improve ad-hoc retrieval. We propose an LDA-based document model within the language modeling framework, and evaluate it on several TREC collections. Gibbs sampling is employed to conduct approximate inference in LDA and the computational complexity is analyzed. We show that improvements over retrieval using cluster-based models can be obtained with reasonable efficiency.},\n bibtype = {article},\n author = {Wei, Xing and Croft, W Bruce}\n}","author_short":["Wei, X.","Croft, W., B."],"urls":{"Paper":"http://bibbase.org/service/mendeley/371589bb-c770-37ff-8193-93c6f25ffeb1/file/30903801-04f2-65f1-116c-1869182b5a67/LDA-Based_Document_Models_for_Ad-hoc_Retrieval.pdf.pdf","Website":"http://delivery.acm.org/10.1145/1150000/1148204/p178-wei.pdf?ip=128.227.11.255&id=1148204&acc=ACTIVE%20SERVICE&key=5CC3CBFF4617FD07%2EC2A817F22E85290F%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&__acm__=1517849765_76c2307841baea334709cecf679f9fb3"},"bibbaseid":"wei-croft-ldabaseddocumentmodelsforadhocretrieval","role":"author","keyword":["Document Model","Experimentation Keywords Information Retrieval","Language Model","Latent Dirichlet Allocation (LDA)","Topic Model"],"downloads":0},"search_terms":["lda","based","document","models","hoc","retrieval","wei","croft"],"keywords":["document model","experimentation keywords information retrieval","language model","latent dirichlet allocation (lda)","topic model"],"authorIDs":[]}