There has been an ever-growing interest in tasks targeting Natural Language Understanding and Reasoning. Alth ough deep learning models have achieved human-like performance in many such tasks, it has also been repeatedly shown that they lack the precision, gen eralization power, reasoning capabilities, and exp lainability found in more traditional, symbolic ap proaches. Thus, current research has started emplo ying hybrid methods, combining the strengths of ea ch tradition and mitigating its weaknesses. This w orkshop would like to promote this research direct ion and foster fruitful dialog between the two dis ciplines by bringing together researchers working on hybrid methods in any subfield of Natural Langu age Understanding and Reasoning.
\nT he 5th iteration of the NALOMA (Natural Logic Meet s Machine Learning) workshop is co-located with ES SLLI.
\nThe NALOMA workshop i nvites submissions on any (theoretical or computat ional) aspect of hybrid methods concerning Natural Language Understanding and Reasoning (NLU&R). NALOMA accepts archival papers (to appear in the ACL anthology proceedings) and (non-archival) exte nded abstracts. Both accepted papers and exte nded abstracts are expected to be presented at the workshop. Extended abstracts will be presented as talks or posters at the discretion of the program committee.
\n