2 papers
cs.CL2023
Does Character-level Information Always Improve DRS-based Semantic Parsing?
Tomoya Kurosawa, Hitomi Yanaka
Even in the era of massive language models, it has been suggested that character-level representations improve the performance of neural models. The state-of-the-art neural semanti…
cs.CL2022
Logical Inference for Counting on Semi-structured Tables
Tomoya Kurosawa, Hitomi Yanaka
Recently, the Natural Language Inference (NLI) task has been studied for semi-structured tables that do not have a strict format. Although neural approaches have achieved high perf…