HyperAI초신경

Dialogue Act Classification On Switchboard

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
HGRU + Beam Search + Guided attention	85.0	Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
Speaker	83.2	Speaker Turn Modeling for Dialogue Act Classification
Bi-RNN + Self-Attention + Context	82.9	Dialogue Act Classification with Context-Aware Self-Attention
DAH-CRF	82.3	A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
ALDMN	81.5	Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
CRF-ASN	81.3	Dialogue Act Recognition via CRF-Attentive Structured Network
Bi-LSTM-CRF	79.2	Dialogue Act Sequence Labeling using Hierarchical encoder with CRF
Pretrained Hierarchical Transformer	79.2	Hierarchical Pre-training for Sequence Labelling in Spoken Dialog
Utt-Att-BiRNN	77.42	Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks
RNN with 3 utterances in context	77.34	A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks
CNN[[Lee and Dernoncourt2016]]	73.1	Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks

0 of 11 row(s) selected.

Dialogue Act Classification On Switchboard | SOTA | HyperAI초신경