AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Modeling Dialogues with Hashcode Representations: A Nonparametric Approach

Sahil Garg, Irina Rish, Guillermo Cecchi, Palash Goyal, Sarik Ghazarian, Shuyang Gao, Greg Ver Steeg, Aram Galstyan

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use LSH-RkNN hashing model instead of VHREDdialogue model · Depression human evalAppropriate (%): 9.5 -> 28.7Improved
use LSH-RkNN instead of VHREDdialogue model · Depression human evalDiverse (%): 0.7 -> 35.1Improved
use LSH-RkNN instead of VHREDdialogue model · Larry King human evalAppropriate (%): 5.3 -> 31.7Improved
use LSH-RLSTM instead of VHREDdialogue model · Larry King human evalDiverse (%): 0.0 -> 36.7Improved
use LSH-RLSTM instead of VHREDdialogue model · Depression Therapyembedding average: 0.48 -> 0.64Improved
use LSH-RkNN instead of VHREDdialogue model · Depression Therapyembedding extrema: 0.29 -> 0.37Improved
use LSH-RkNN instead of VHREDdialogue model · Twitterembedding average: 0.53 -> 0.61±0.17Improved
use LSH-RkNN instead of VHREDdialogue model · Twitterembedding extrema: 0.38 -> 0.25±0.09Hurt
use LSH-RLSTM instead of VHREDdialogue model · Larry Kingembedding greedy: 0.72±0.25 -> 0.58±0.21Hurt
generate responses with hashed N-gram language model instead of selecting from training setLSH-RkNN · Depression human eval (300 samples)Appropriate (%): 36.8 -> 33.8No clear effect
generate responses with hashed N-gram language model instead of selecting from training setLSH-RkNN · Depression human eval (300 samples)Diverse (%): 80 -> 12.0Hurt
replace RkNN hashing with RLSTM hashinghashcode model · TwitterMI LB: 17.3±0.1 -> 41.9±0.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy