AI Paper Atlas

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

Addressee and Response Selection in Multi-Party Conversations With Speaker Interaction RNNs

Rui Zhang, Honglak Lee, Lazaros Polymenakos, Dragomir Radev

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 63 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 role-sensitive speaker updates and joint addressee-response selectionSI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15ADR-RES accuracy: 54.88 -> 67.30Improved
use role-sensitive speaker updates and joint addressee-response selectionSI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15ADR-RES accuracy: 27.19 -> 35.76Improved
use role-sensitive speaker updates and joint addressee-response selectionSI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15ADR accuracy: 68.54 -> 80.47Improved
use role-sensitive speaker updates and joint addressee-response selectionSI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15RES accuracy: 36.93 -> 40.83Improved
add role-specific parameters for sender, addressee, and observer update units (ablation)SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15ADR-RES accuracy: 59.47 -> 67.30Improved
add role-specific parameters for sender, addressee, and observer update units (ablation)SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15ADR-RES accuracy: 28.45 -> 35.76Improved
jointly select the addressee and response rather than selecting them separately (ablation)SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15ADR-RES accuracy: 63.40 -> 67.30Improved
jointly select the addressee and response rather than selecting them separately (ablation)SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15ADR-RES accuracy: 32.53 -> 35.76Improved

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