# Unsupervised, Efficient and Semantic Expertise Retrieval

arXiv: https://arxiv.org/abs/1608.06651 · HTML: https://mlsanity.com/paper/1608.06651/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2016.

## Built on by (most cited first, 7 of 7)

- [ExpFinder: An Ensemble Expert Finding Model Integrating N-gram Vector Space Model and μCO-HITS](https://mlsanity.com/paper/2101.06821/) (2021)
- [An Explanatory Query-Based Framework for Exploring Academic Expertise](https://mlsanity.com/paper/2105.13728/) (2021)
- [Modeling Proficiency with Implicit User Representations](https://mlsanity.com/paper/2110.08011/) (2021)
- [API-Miner: an API-to-API Specification Recommendation Engine](https://mlsanity.com/paper/2212.07253/) (2022)
- [Explaining Expert Search and Team Formation Systems with ExES](https://mlsanity.com/paper/2405.12881/) (2024)
- [On the Biased Assessment of Expert Finding Systems](https://mlsanity.com/paper/2410.05018/) (2024)
- [From Unstructured to Structured: LLM-Guided Attribute Graphs for Entity Search and Ranking](https://mlsanity.com/paper/2604.27410/) (2026)

## Abstract (arXiv)

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.