Justus-Jonas Erker — accepted AI-conference papers

2024

Triple-Encoders: Representations That Fire Together, Wire Together

Justus-Jonas Erker, Florian Mai, Nils Reimers, Gerasimos Spanakis, Iryna Gurevych

ACL 2024long

Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost.Curved Contrastive Learning, a representation learning method that encodes relative distances between utterances into the embedding space via a bi-encoder, has recently shown promising results for di…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning

Justus-Jonas Erker, Stefan Schaffer, Gerasimos Spanakis

ACL 2023findings

Inspired by the curvature of space-time, we introduce Curved Contrastive Learning (CCL), a novel representation learning technique for learning the relative turn distance between utterance pairs in multi-turn dialogues. The resulting bi-encoder models can guide transformers as a response ranking mod…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗