2016/04/11 by C Gysel, Christophe Van Gysel, Maarten de Rijke +1 · 57 citations
Computer Science · Mathematics · #Artificial intelligence #Computer science #Deep learning #Discriminative model #Expert finding and Q&A systems #Feature (linguistics) #Feature engineering #Feature vector #Generative grammar #Generative model #Inference #Information Retrieval and Search Behavior #Learning to rank #Machine learning #Matching (statistics) #Mathematics #Pattern recognition (psychology) #Probabilistic logic #Ranking (information retrieval) #Relevance (law) #Task (project management) #Topic Modeling #Unsupervised learning #cs.AI #cs.CL #cs.IR #cs.LG
paper · pdf · doi:10.1145/2872427.2882974
WWW2016, Proceedings of the 25th International Conference on World Wide Web. 2016
openalex publication_date 2016/04/11 · arxiv created 2017/09/17 · arxiv updated 2017/09/19 · openalex created_date 2020/11/23 · openalex updated_date 2026/08/05
We introduce an unsupervised discriminative model for the task of retrieving experts in online document collections. We exclusively employ textual evidence and avoid explicit feature engineering by learning distributed word representations in an unsupervised way. We compare our model to state-of-the-art unsupervised statistical vector space and probabilistic generative approaches. Our proposed log-linear model achieves the retrieval performance levels of state-of-the-art document-centric methods with the low inference cost of so-called profile-centric approaches. It yields a statistically significant improved ranking over vector space and generative models in most cases, matching the performance of supervised methods on various benchmarks. That is, by using solely text we can do as well as methods that work with external evidence and/or relevance feedback. A contrastive analysis of rankings produced by discriminative and generative approaches shows that they have complementary strengths due to the ability of the unsupervised discriminative model to perform semantic matching.