2k citations
- Ghent UniversityBE28 papers
- KU LeuvenBE27 papers
- University of AntwerpBE17 papers
- Universitat Politècnica de CatalunyaES4 papers
- Vrije Universiteit BrusselBE4 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Ghent University HospitalBE3 papers
- Hasselt UniversityBE3 papers
- Politecnico di TorinoIT3 papers
- Sapienza University of RomeIT3 papers
- University College LondonGB3 papers
- University of AmsterdamNL3 papers
Showing cs.IRShow all
3 papers · 1 filter
cs.IR2016★ 200 cited
Representation learning for very short texts using weighted word embedding aggregation
Cedric De Boom, Steven Van Canneyt, Thomas Demeester +1
Short text messages such as tweets are very noisy and sparse in their use of vocabulary. Traditional textual representations, such as tf-idf, have difficulty grasping the semantic…
cs.IR2015★ 96 cited
Learning Semantic Similarity for Very Short Texts
Cedric De Boom, Steven Van Canneyt, Steven Bohez +2
Levering data on social media, such as Twitter and Facebook, requires information retrieval algorithms to become able to relate very short text fragments to each other. Traditional…
cs.IR2015★ 10 cited
Predicting Relevance based on Assessor Disagreement: Analysis and Practical Applications for Search Evaluation
Thomas Demeester, Robin Aly, Djoerd Hiemstra +2
Evaluation of search engines relies on assessments of search results for selected test queries, from which we would ideally like to draw conclusions in terms of relevance of the re…