Sosuke Nishikawa — accepted AI-conference papers

2025

Search Query Embeddings via User-behavior-driven Contrastive Learning

Sosuke Nishikawa, Jun Hirako, Nobuhiro Kaji, Koki Watanabe, Hiroki Asano, Souta Yamashiro +1

NAACL 2025industry

Universal query embeddings that accurately capture the semantic meaning of search queries are crucial for supporting a range of query understanding (QU) tasks within enterprises.However, current embedding approaches often struggle to effectively represent queries due to the shortness of search queri…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

EASE: Entity-Aware Contrastive Learning of Sentence Embedding

Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, Isao Echizen

NAACL 2022long

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training…

Cited by 38 Source ↗PDF ↗code ↗Scholar ↗