Unsupervised, Efficient and Semantic Expertise Retrieval
This addresses the need for efficient and semantic expert retrieval in domains like academia or industry, offering an incremental improvement by combining the strengths of discriminative and generative models without requiring external data.
The paper tackles the problem of retrieving experts from online document collections using an unsupervised discriminative model that relies solely on textual evidence, achieving retrieval performance comparable to state-of-the-art supervised methods and statistically significant improvements over other unsupervised approaches.
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.