natural-language-processing-10

Dialog Act Classification

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in dialog-act-classification-10

Trend

Dataset

Best Model

Actions

Switchboard dialogue act corpus

Libraries

i

Use these libraries to find dialog-act-classification-10 models and implementations

Datasets

CPED

SILICONE Benchmark

Subtasks

No subtasks available.

Most implemented papers

Optimizing neural network hyperparameters with Gaussian processes for dialog act classification

Franck Dernoncourt, Ji Young Lee•Mon Sep 26 2016

Using a previously published ANN model yielding state-of-the-art results for dialog act classification, it is demonstrated that optimizing hyperparameters using GP further improves the results, and reduces the computational time by a factor of 4 compared to a random search.

28

Content

0

Paper Graph

Probabilistic Word Association for Dialogue Act Classification with Recurrent Neural Networks

Nathan Duran, Steve Battle•Sun Sep 02 2018

A novel probabilistic method of utterance representation is presented and a RNN sentence model for out-of-context DA Classification is described and generated from keywords selected for their frequency association with certain DA’s.

9 0

Paper Graph

Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks

Chandrakant Bothe, C. Weber, S. Magg, Stefan Wermter•Tue May 15 2018

An utterance-level attention-based bidirectional recurrent neural network (Utt-Att-BiRNN) model to analyze the importance of preceding utterances to classify the current one and to show that context-based learning not only improves the performance but also achieves higher confidence in the classification.

17 0

Paper Graph

Privacy Guarantees for De-identifying Text Transformations

D. Klakow, David Ifeoluwa Adelani, Thomas Kleinbauer, A. Davody•Thu Aug 06 2020

This paper derives formal privacy guarantees for general text transformation-based de-identification methods on the basis of Differential Privacy and measures the effect that different ways of masking private information in dialog transcripts have on a subsequent machine learning task.

17 0

Paper Graph

Self-Governing Neural Networks for On-Device Short Text Classification

Zornitsa Kozareva, Sujith Ravi•Sun Dec 31 2017

The findings show that SGNNs are effective at capturing low-dimensional semantic text representations, while maintaining high accuracy, and extensive evaluation on dialog act classification shows significant improvement over state-of-the-art results.

38 0

Paper Graph

Sentence encoding for Dialogue Act classification

Nathan Duran, Steve Battle, Jim E. Smith•Mon Nov 01 2021

It is found that viable input sequence lengths, and vocabulary sizes, can be much smaller than is typically used in DA classification experiments, yielding no significant improvements beyond certain thresholds, and in some cases the contextual sentence representations generated by language models do not reliably outperform supervised methods.

11 0

Paper Graph

DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition

I. Tsang, Bowen Xing•Mon Mar 07 2022

A novel model dubbed DARER is proposed, which first generates the context-, speaker- and temporal-sensitive utterance representations via modeling SATG, then conducts recurrent dual-task relational reasoning on DRTG, in which process the estimated label distributions act as key clues in prediction-level interactions.

21 0

Paper Graph

CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI

Minlie Huang, Yirong Chen, Weiquan Fan, Xiaofen Xing, Jianxin Pang, W. Han, Qianfeng Tie, Xiangmin Xu•Sat May 28 2022

This work proposes CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic, to be widely adopted by the NLP community as a new open benchmark for conversational AI research.

38 0

Paper Graph

TOD-Flow: Modeling the Structure of Task-Oriented Dialogues

Yiwei Lyu, Lajanugen Logeswaran, Sungryull Sohn, A. Liu, Dong-Ki Kim, Dongsub Shim, Honglak Lee•Wed Dec 06 2023

This work proposes a novel approach focusing on inferring the TOD-Flow graph from dialogue data annotated with dialog acts, uncovering the underlying task structure in the form of a graph that better resembles human-annotated graphs compared to prior approaches.

4 0

Paper Graph

Adding a benchmark result helps the community track progress.