Team DUTH reports that XLM-RoBERTa dense retrieval with re-ranking yields stronger MAP/MRR/precision on Portuguese humor documents than on English ones in the JOKER benchmark.
InProceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multilingual Humour-Aware Retrieval with Dense and Re-Ranking Models
Team DUTH reports that XLM-RoBERTa dense retrieval with re-ranking yields stronger MAP/MRR/precision on Portuguese humor documents than on English ones in the JOKER benchmark.