作者位次 #4/12ACL 2026Poster· Natural Language Processing
SEA - BED : How Do Embedding Models Represent S outheast A sian Languages?
Wuttikorn Ponwitayarat · Peerat Limkonchotiwat · Raymond Ng · Jann Railey Montalan · Thura Aung · Jian Gang Ngui · Yosephine Susanto · William Chandra Tjhi · Panuthep Tasawong · Erik Cambria · Ekapol Chuangsuwanich · Sarana Nutanong
摘要
Multilingual text embeddings are often assumed to encode meaning in a perspective-independent semantic space, yielding stable similarity judgments across tasks and languages. Our results show that this assumption does not hold in practice. We introduce SEA-BED, a large-scale benchmark covering 10...