Iryna Gurevych, Nils Reimers, Florian Mai, Justus-Jonas Erker, Gerasimos Spanakis
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Search-based dialog models typically reencode 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 dialog modeling at far superior efficiency. While high efficiency is achieved through independently encoding utterances, this ignores the importance of contextualization. To overcome this issue, this study introduces triple-encoders, which efficiently compute distributed utterance mixtures from these independently encoded utterances through a novel hebbian inspired co-occurrence learning objective in a self-organizing manner, without using any weights, i.e., merely through local interactions. Empirically, we find that triple-encoders lead to a substantial improvement over bi-encoders, and even to better zeroshot generalization than single-vector representation models without requiring re-encoding. Our code 1 and model 2 are publicly available.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.12332")
get_code_for_paper("2402.12332")
have("2402.12332")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.12332.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.12332)
Connect an agent — have() is free.