Unsupervised, Efficient and Semantic Expertise Retrieval

Abstract

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.

WWW2016, Proceedings of the 25th International Conference on World Wide Web. 2016

References in corpus (4)

• Distributed Representations of Words and Phrases and their Compositionality
• ADADELTA: An Adaptive Learning Rate Method
• Natural Language Processing (almost) from Scratch
• Using Rank Aggregation for Expert Search in Academic Digital Libraries

Cited by in corpus (13)

• Neural Vector Spaces for Unsupervised Information Retrieval
• Learning Latent Vector Spaces for Product Search
• WISER: A Semantic Approach for Expert Finding in Academia based on Entity Linking
• ExpFinder: An Ensemble Expert Finding Model Integrating $N$-gram Vector Space Model and $\mu$CO-HITS
• Quality-aware skill translation models for expert finding on StackOverflow
• Expert Finding in Heterogeneous Bibliographic Networks with Locally-trained Embeddings
• Semantic Entity Retrieval Toolkit
• Neural Ranking Models with Weak Supervision
• Getting Started with Neural Models for Semantic Matching in Web Search
• New Datasets and a Benchmark of Document Network Embedding Methods for Scientific Expert Finding
• Remedies against the Vocabulary Gap in Information Retrieval
• Person Entity Profiling Framework: Identifying, Integrating and Visualizing Online Freely Available Entity-Related Information
• Modeling Proficiency with Implicit User Representations